display correct commit

display version

Dockerfile.full

@@ -4,7 +4,7 @@ FROM node:23-alpine AS ui-builder
 WORKDIR /app/ui
 
 # Install pnpm
-RUN corepack enable pnpm && corepack prepare pnpm@latest --activate
+RUN corepack enable pnpm && corepack prepare pnpm@10.15.0 --activate
 
 # Copy UI source
 COPY ui/package.json ui/pnpm-lock.yaml* ./

docs/provider/configuration.md

@@ -78,9 +78,15 @@ Which mints to accept payments from:
 
 Automatic profit withdrawal:
 
-| Setting               | Description                     |
-| --------------------- | ------------------------------- |
-| **Lightning Address** | Your LN address for withdrawals |
+| Setting                              | Description                                                                                                | Default |
+| ------------------------------------ | ---------------------------------------------------------------------------------------------------------- | ------- |
+| **Lightning Address**                | Your LN address for withdrawals                                                                            | —       |
+| **Minimum Payout (sat)**             | Min available balance (in sats) before profit is paid out. Applies to both `sat` and `msat` mints (auto-converted). | `210`   |
+| **Payout Interval (seconds)**        | How often the payout loop wakes up and checks balances                                                     | `900`   |
+
+All payout amounts must be positive. Set the minimums above your wallet's
+minimum-invoice constraint (typically 1 sat) and high enough to amortise
+routing fees.
 
 ### Security
 
@@ -126,6 +132,8 @@ Use environment variables for:
 | `ENABLE_ANALYTICS_SHARING` | Enable usage analytics sharing to Nostr | `true`                         |
 | `CASHU_MINTS`        | Comma-separated mint URLs         | `https://mint.minibits.cash/Bitcoin` |
 | `RECEIVE_LN_ADDRESS` | Lightning address for withdrawals | —                                    |
+| `MIN_PAYOUT_SAT`     | Min payout balance in sats (applies to all mints) | `210`                |
+| `PAYOUT_INTERVAL_SECONDS` | Payout loop interval (seconds) | `900`                            |
 | `TOR_PROXY_URL`      | SOCKS5 proxy for Tor              | `socks5://127.0.0.1:9050`            |
 | `CORS_ORIGINS`       | Allowed CORS origins              | `*`                                  |
 | `RELAYS`             | Nostr relays (comma-separated)    | (default set)                        |

routstr/algorithm.py

@@ -195,14 +195,15 @@ def create_model_mappings(
 
             # Add to unique models
             base_id = get_base_model_id(model_to_use.id)
-            if not is_openrouter or base_id not in unique_models:
+            unique_key = model_to_use.forwarded_model_id or base_id
+            if not is_openrouter or unique_key not in unique_models:
                 unique_model = model_to_use.copy(
                     update={
                         "id": base_id,
                         "upstream_provider_id": upstream.provider_type,
                     }
                 )
-                unique_models[base_id] = unique_model
+                unique_models[unique_key] = unique_model
 
             # Get all aliases for this model
             aliases = resolve_model_alias(
@@ -272,18 +273,19 @@ def create_model_mappings(
             continue
 
         base_id = get_base_model_id(model_to_use.id)
+        unique_key = model_to_use.forwarded_model_id or base_id
         is_openrouter = (
             getattr(upstream_for_override, "base_url", "")
             == "https://openrouter.ai/api/v1"
         )
-        if not is_openrouter or base_id not in unique_models:
+        if not is_openrouter or unique_key not in unique_models:
             unique_model = model_to_use.copy(
                 update={
                     "id": base_id,
                     "upstream_provider_id": upstream_for_override.provider_type,
                 }
             )
-            unique_models[base_id] = unique_model
+            unique_models[unique_key] = unique_model
 
         try:
             aliases = resolve_model_alias(
@@ -322,7 +324,26 @@ def create_model_mappings(
     provider_map: dict[str, list["BaseUpstreamProvider"]] = {}
 
     def alias_priority(model: "Model", alias: str) -> int:
-        """Rank how strong the mapping of alias->model is."""
+        """Rank how strong the mapping of alias->model is.
+
+        forwarded_model_id is the most specific identifier (set per-provider
+        instance), so a match there should beat a model_id match. This way,
+        when multiple providers have the same model_id but different
+        forwarded_model_ids, the one whose forwarded_model_id equals the
+        requested alias wins.
+        """
+        if (
+            model.forwarded_model_id
+            and model.forwarded_model_id.lower() == alias
+        ):
+            return 5
+
+        if (
+            model.id
+            and model.id.lower() == alias
+        ):
+            return 4
+
         model_base = get_base_model_id(model.id)
         if model_base == alias:
             return 3

routstr/balance.py

@@ -211,8 +211,20 @@ async def _refund_cache_set(authorization: str, value: dict[str, str]) -> None:
         _refund_cache[key] = (expiry, value)
 
 
+async def _lookup_key_no_create(
+    bearer_value: str, session: AsyncSession
+) -> ApiKey | None:
+    """Look up an existing API key without creating one Used by the refund endpoint"""
+    if bearer_value.startswith("sk-"):
+        return await session.get(ApiKey, bearer_value[3:])
+    if bearer_value.startswith("cashu"):
+        hashed = hashlib.sha256(bearer_value.encode()).hexdigest()
+        return await session.get(ApiKey, hashed)
+    return None
+
+
 async def _restore_balance(
-    session: AsyncSession, hashed_key: str, balance: int, reserved_balance: int
+    session: AsyncSession, hashed_key: str, balance: int, reserved_balance: int, mint_url: str
 ) -> None:
     """Restore balance after a failed refund mint attempt."""
     restore_stmt = (
@@ -227,7 +239,7 @@ async def _restore_balance(
     await session.commit()
     logger.info(
         "refund_wallet_endpoint: balance restored after mint failure",
-        extra={"hashed_key": hashed_key, "restored_balance": balance},
+        extra={"hashed_key": hashed_key, "restored_balance": balance, "mint_url": mint_url},
     )
 
 
@@ -282,7 +294,12 @@ async def refund_wallet_endpoint(
         )
 
     bearer_value: str = authorization[7:]
-    key: ApiKey = await validate_bearer_key(bearer_value, session)
+    key: ApiKey | None = await _lookup_key_no_create(bearer_value, session)
+    if key is None:
+        raise HTTPException(
+            status_code=401,
+            detail="Key not found. Deposit first via /v1/wallet/create before requesting a refund.",
+        )
 
     if key.total_balance <= 0:
         if cached := await _refund_cache_get(bearer_value):
@@ -337,21 +354,26 @@ async def refund_wallet_endpoint(
         )
 
     # --- MINT: balance is locked at zero, safe to create the refund token ---
+    # Proofs from untrusted mints are swapped to primary_mint on receive.
+    # Use primary_mint unless key.refund_mint_url is an explicitly trusted mint.
+    effective_refund_mint = (
+        key.refund_mint_url
+        if key.refund_mint_url and key.refund_mint_url in settings.cashu_mints
+        else settings.primary_mint
+    )
     try:
         if key.refund_address:
-            from .core.settings import settings as global_settings
-
             await send_to_lnurl(
                 remaining_balance,
                 key.refund_currency or "sat",
-                key.refund_mint_url or global_settings.primary_mint,
+                effective_refund_mint,
                 key.refund_address,
             )
             result = {"recipient": key.refund_address}
         else:
             refund_currency = key.refund_currency or "sat"
             token = await send_token(
-                remaining_balance, refund_currency, key.refund_mint_url
+                remaining_balance, refund_currency, effective_refund_mint
             )
             result = {"token": token}
 
@@ -373,21 +395,32 @@ async def refund_wallet_endpoint(
 
     except HTTPException:
         # Minting failed — restore the debited balance
-        await _restore_balance(session, key.hashed_key, pre_debit_balance, pre_debit_reserved)
+        await _restore_balance(session, key.hashed_key, pre_debit_balance, pre_debit_reserved, key.refund_mint_url or "")
         raise
     except Exception as e:
         # Minting failed — restore the debited balance
-        await _restore_balance(session, key.hashed_key, pre_debit_balance, pre_debit_reserved)
+        await _restore_balance(session, key.hashed_key, pre_debit_balance, pre_debit_reserved, key.refund_mint_url or "")
         error_msg = str(e)
+        logger.error(
+            "refund_wallet_endpoint: mint/send failed",
+            extra={
+                "error": error_msg,
+                "error_type": type(e).__name__,
+                "hashed_key": key.hashed_key,
+                "remaining_balance": remaining_balance,
+                "refund_currency": key.refund_currency,
+                "refund_mint_url": key.refund_mint_url,
+                "has_refund_address": bool(key.refund_address),
+            },
+        )
         if (
             "mint" in error_msg.lower()
             or "connection" in error_msg.lower()
-            or isinstance(e, Exception)
-            and "ConnectError" in str(type(e))
+            or "ConnectError" in str(type(e))
         ):
-            raise HTTPException(status_code=503, detail="Mint service unavailable")
+            raise HTTPException(status_code=503, detail=f"Mint service unavailable: {error_msg}")
         else:
-            raise HTTPException(status_code=500, detail="Refund failed")
+            raise HTTPException(status_code=500, detail=f"Refund failed: {error_msg}")
 
     await _refund_cache_set(bearer_value, result)
 

routstr/core/admin.py

@@ -6,6 +6,7 @@ from pathlib import Path
 
 from fastapi import APIRouter, Depends, HTTPException, Query, Request
 from pydantic import BaseModel, RootModel
+from pydantic.v1 import ValidationError as PydanticValidationError
 from sqlmodel import select
 
 from ..payment.models import _row_to_model, list_models
@@ -160,8 +161,13 @@ async def update_settings(request: Request, update: SettingsUpdate) -> dict:
         if field in settings_data:
             del settings_data[field]
 
-    async with create_session() as session:
-        new_settings = await SettingsService.update(settings_data, session)
+    try:
+        async with create_session() as session:
+            new_settings = await SettingsService.update(settings_data, session)
+    except PydanticValidationError as e:
+        # Surface validation issues (e.g. non-positive payout amounts)
+        # as a clean 400 instead of a 500.
+        raise HTTPException(status_code=400, detail=e.errors()) from e
     data = new_settings.dict()
     if "upstream_api_key" in data:
         data["upstream_api_key"] = "[REDACTED]" if data["upstream_api_key"] else ""

routstr/core/main.py

@@ -30,6 +30,7 @@ from .db import create_session, init_db, run_migrations
 from .exceptions import general_exception_handler, http_exception_handler
 from .logging import get_logger, setup_logging
 from .middleware import LoggingMiddleware
+from .not_found import _NOT_FOUND_HTML, not_found_catch_all  # noqa: F401
 from .settings import SettingsService
 from .settings import settings as global_settings
 from .version import __version__

routstr/core/not_found.py

@@ -0,0 +1,55 @@
+"""Shared 404 handler used by the proxy catch-all and tests."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from fastapi import Request
+from fastapi.responses import HTMLResponse, JSONResponse, Response
+
+_NOT_FOUND_HTML_FILE = Path(__file__).parent.parent.parent / "ui_out" / "404.html"
+
+
+def _read_not_found_html() -> str | None:
+    try:
+        return _NOT_FOUND_HTML_FILE.read_text(encoding="utf-8")
+    except OSError:
+        return None
+
+
+_NOT_FOUND_HTML: str | None = _read_not_found_html()
+
+
+def build_not_found_response(request: Request, path: str) -> Response:
+    """Return a 404 response.
+
+    HTML 404 page only for GET requests from browsers (Accept: text/html).
+    All POST requests and API clients receive a JSON 404.
+    """
+    accept = request.headers.get("accept", "").lower()
+    prefers_html = (
+        request.method == "GET"
+        and "text/html" in accept
+        and "application/json" not in accept
+    )
+    request_id = getattr(request.state, "request_id", "unknown")
+
+    if prefers_html and _NOT_FOUND_HTML is not None:
+        return HTMLResponse(content=_NOT_FOUND_HTML, status_code=404)
+
+    return JSONResponse(
+        status_code=404,
+        content={
+            "error": {
+                "message": f"Path '/{path}' not found",
+                "type": "not_found",
+                "code": 404,
+            },
+            "request_id": request_id,
+        },
+    )
+
+
+async def not_found_catch_all(request: Request, path: str) -> Response:
+    """ASGI handler form of :func:`build_not_found_response`."""
+    return build_not_found_response(request, path)

routstr/core/settings.py

@@ -41,6 +41,15 @@ class Settings(BaseSettings):
     primary_mint: str = Field(default="", env="PRIMARY_MINT_URL")
     primary_mint_unit: str = Field(default="sat", env="PRIMARY_MINT_UNIT")
 
+    # Lightning payout configuration
+    # Minimum available balance (in satoshis) before profit is paid out over
+    # Lightning
+    min_payout_sat: int = Field(default=210, gt=0, env="MIN_PAYOUT_SAT")
+    # Interval (seconds) between periodic payout attempts. Must be positive.
+    payout_interval_seconds: int = Field(
+        default=900, gt=0, env="PAYOUT_INTERVAL_SECONDS"
+    )
+
     # Pricing
     # Default behavior: derive pricing from MODELS
     # If fixed_pricing is True -> use fixed_cost_per_request and ignore tokens

routstr/core/version.py

@@ -55,9 +55,9 @@ def _on_tagged_release() -> bool:
     if tag:
         return tag.lstrip("v") == BASE_VERSION
     described = _run_git("describe", "--tags", "--exact-match", "HEAD")
-    if not described:
-        return False
-    return described.lstrip("v") == BASE_VERSION
+    if described and described.lstrip("v") == BASE_VERSION:
+        return True
+    return False
 
 
 @lru_cache(maxsize=1)

routstr/payment/cost_calculation.py

@@ -18,6 +18,10 @@ class CostData(BaseModel):
     total_usd: float = 0.0
     input_tokens: int = 0
     output_tokens: int = 0
+    cache_read_input_tokens: int = 0
+    cache_creation_input_tokens: int = 0
+    cache_read_msats: int = 0
+    cache_creation_msats: int = 0
 
 
 class MaxCostData(CostData):
@@ -29,11 +33,10 @@ class CostDataError(BaseModel):
     code: str
 
 
-async def calculate_cost(  # todo: can be sync
+async def calculate_cost(
     response_data: dict, max_cost: int, session: AsyncSession
 ) -> CostData | MaxCostData | CostDataError:
-    """
-    Calculate the cost of an API request based on token usage.
+    """Calculate the cost of an API request based on token usage.
 
     Args:
         response_data: Response data containing usage information
@@ -51,6 +54,7 @@ async def calculate_cost(  # todo: can be sync
         },
     )
 
+    # Check for usage data
     if "usage" not in response_data or response_data["usage"] is None:
         logger.warning(
             "No usage data in response — billing at MaxCostData with zero "
@@ -74,77 +78,25 @@ async def calculate_cost(  # todo: can be sync
             total_usd=0.0,
             input_tokens=0,
             output_tokens=0,
+            cache_read_input_tokens=0,
+            cache_creation_input_tokens=0,
+            cache_read_msats=0,
+            cache_creation_msats=0,
         )
 
     usage_data = response_data["usage"]
 
-    def parse_token_count(value: object) -> int:
-        if isinstance(value, bool):
-            return 0
-        if isinstance(value, int):
-            return max(0, value)
-        if isinstance(value, float):
-            return max(0, int(value))
-        if isinstance(value, str):
-            try:
-                return max(0, int(float(value)))
-            except ValueError:
-                return 0
-        return 0
+    # Extract token counts
+    input_tokens = _extract_token_pair(usage_data, "prompt_tokens", "input_tokens")
+    output_tokens = _extract_token_pair(usage_data, "completion_tokens", "output_tokens")
 
-    input_tokens = parse_token_count(usage_data.get("prompt_tokens", 0))
-    output_tokens = parse_token_count(usage_data.get("completion_tokens", 0))
-    input_tokens = (
-        input_tokens
-        if input_tokens != 0
-        else parse_token_count(usage_data.get("input_tokens", 0))
-    )
-    output_tokens = (
-        output_tokens
-        if output_tokens != 0
-        else parse_token_count(usage_data.get("output_tokens", 0))
-    )
-    input_tokens = (
-        input_tokens
-        if input_tokens != 0
-        else parse_token_count(response_data.get("usage", {}).get("input_tokens", 0))
-    )
-    output_tokens = (
-        output_tokens
-        if output_tokens != 0
-        else parse_token_count(response_data.get("usage", {}).get("output_tokens", 0))
-    )
-
-    usd_cost = 0.0
-    input_usd = 0.0
-    output_usd = 0.0
-
-    if "cost_details" in usage_data:
-        usd_cost = float(
-            usage_data["cost_details"].get("upstream_inference_cost", 0) or 0
-        )
-        input_usd = float(
-            usage_data["cost_details"].get("upstream_inference_prompt_cost", 0) or 0
-        )
-        output_usd = float(
-            usage_data["cost_details"].get("upstream_inference_completions_cost", 0)
-            or 0
-        )
-
-    # Fallback to cost field if upstream_inference_cost is 0
-    if usd_cost == 0 and "cost" in usage_data:
-        try:
-            usd_cost = float(usage_data.get("cost", 0) or 0)
-        except Exception:
-            pass
-
-    MSATS_PER_1K_INPUT_TOKENS: float = (
-        float(settings.fixed_per_1k_input_tokens) * 1000.0
-    )
-    MSATS_PER_1K_OUTPUT_TOKENS: float = (
-        float(settings.fixed_per_1k_output_tokens) * 1000.0
+    # Extract cache tokens (handles OpenAI vs Anthropic formats)
+    cache_read_tokens, cache_creation_tokens, input_tokens = _extract_cache_tokens(
+        usage_data, input_tokens
     )
 
+    # Try USD cost first
+    usd_cost = _resolve_usd_cost(usage_data, response_data)
     if usd_cost > 0:
         if input_tokens == 0 and output_tokens == 0:
             logger.warning(
@@ -163,53 +115,21 @@ async def calculate_cost(  # todo: can be sync
                 },
             )
         try:
-            sats_per_usd = 1.0 / sats_usd_price()
-            cost_in_sats = usd_cost * sats_per_usd
-            cost_in_msats = math.ceil(cost_in_sats * 1000)
-
-            input_msats = 0
-            output_msats = 0
-
-            if input_usd > 0 or output_usd > 0:
-                input_msats = int((input_usd * sats_per_usd) * 1000)
-                output_msats = int((output_usd * sats_per_usd) * 1000)
-            else:
-                total_tokens = input_tokens + output_tokens
-                if total_tokens > 0:
-                    input_ratio = input_tokens / total_tokens
-                    input_msats = int(cost_in_msats * input_ratio)
-                    output_msats = cost_in_msats - input_msats
-                else:
-                    # No tokens reported — model produced empty output, issue full refund
-                    logger.warning(
-                        "Zero tokens with non-zero USD cost — issuing full refund",
-                        extra={
-                            "usd_cost": usd_cost,
-                            "model": response_data.get("model", "unknown"),
-                        },
-                    )
-                    input_msats = 0
-                    output_msats = 0
-                    cost_in_msats = 0
-
-            logger.info(
-                "Using cost from usage data/details",
-                extra={
-                    "usd_cost": usd_cost,
-                    "cost_in_sats": cost_in_sats,
-                    "cost_in_msats": cost_in_msats,
-                    "model": response_data.get("model", "unknown"),
-                },
+            input_usd = _coerce_usd(
+                usage_data.get("cost_details", {}).get("input_cost", 0)
             )
-
-            return CostData(
-                base_msats=0,
-                input_msats=input_msats,
-                output_msats=output_msats,
-                total_msats=cost_in_msats,
-                total_usd=usd_cost,
-                input_tokens=input_tokens,
-                output_tokens=output_tokens,
+            output_usd = _coerce_usd(
+                usage_data.get("cost_details", {}).get("output_cost", 0)
+            )
+            return _calculate_from_usd_cost(
+                usd_cost,
+                input_usd,
+                output_usd,
+                input_tokens,
+                cache_read_tokens,
+                cache_creation_tokens,
+                output_tokens,
+                response_data,
             )
         except Exception as e:
             logger.warning(
@@ -220,57 +140,22 @@ async def calculate_cost(  # todo: can be sync
                     "model": response_data.get("model", "unknown"),
                 },
             )
-            # Fall through to token-based calculation
 
-    if not settings.fixed_pricing:
-        response_model = response_data.get("model", "")
-        logger.debug(
-            "Using model-based pricing",
-            extra={"model": response_model},
-        )
+    # Fall back to token-based pricing
+    try:
+        pricing_rates = _get_pricing_rates(response_data)
+    except ValueError as e:
+        return CostDataError(message=str(e), code="pricing_error")
 
-        from ..proxy import get_model_instance
+    if pricing_rates is None:
+        input_rate = float(settings.fixed_per_1k_input_tokens) * 1000.0
+        output_rate = float(settings.fixed_per_1k_output_tokens) * 1000.0
+        cache_read_rate = input_rate
+        cache_creation_rate = input_rate
+    else:
+        input_rate, output_rate, cache_read_rate, cache_creation_rate = pricing_rates
 
-        model_obj = get_model_instance(response_model)
-
-        if not model_obj:
-            logger.error(
-                "Invalid model in response",
-                extra={"response_model": response_model},
-            )
-            return CostDataError(
-                message=f"Invalid model in response: {response_model}",
-                code="model_not_found",
-            )
-
-        if not model_obj.sats_pricing:
-            logger.error(
-                "Model pricing not defined",
-                extra={"model": response_model, "model_id": response_model},
-            )
-            return CostDataError(
-                message="Model pricing not defined", code="pricing_not_found"
-            )
-
-        try:
-            mspp = float(model_obj.sats_pricing.prompt)
-            mspc = float(model_obj.sats_pricing.completion)
-        except Exception:
-            return CostDataError(message="Invalid pricing data", code="pricing_invalid")
-
-        MSATS_PER_1K_INPUT_TOKENS = mspp * 1_000_000.0
-        MSATS_PER_1K_OUTPUT_TOKENS = mspc * 1_000_000.0
-
-        logger.info(
-            "Applied model-specific pricing",
-            extra={
-                "model": response_model,
-                "input_price_msats_per_1k": MSATS_PER_1K_INPUT_TOKENS,
-                "output_price_msats_per_1k": MSATS_PER_1K_OUTPUT_TOKENS,
-            },
-        )
-
-    if not (MSATS_PER_1K_OUTPUT_TOKENS and MSATS_PER_1K_INPUT_TOKENS):
+    if not (input_rate and output_rate):
         logger.warning(
             "No token pricing configured — billing at flat MaxCostData. "
             "Token counts %s in the upstream response but cannot be "
@@ -293,12 +178,243 @@ async def calculate_cost(  # todo: can be sync
             total_msats=max_cost,
             input_tokens=input_tokens,
             output_tokens=output_tokens,
+            cache_read_input_tokens=cache_read_tokens,
+            cache_creation_input_tokens=cache_creation_tokens,
+            cache_read_msats=0,
+            cache_creation_msats=0,
         )
 
-    calc_input_msats = round(input_tokens / 1000 * MSATS_PER_1K_INPUT_TOKENS, 3)
+    return _calculate_from_tokens(
+        input_tokens,
+        output_tokens,
+        cache_read_tokens,
+        cache_creation_tokens,
+        input_rate,
+        output_rate,
+        cache_read_rate,
+        cache_creation_rate,
+        response_data,
+    )
 
-    calc_output_msats = round(output_tokens / 1000 * MSATS_PER_1K_OUTPUT_TOKENS, 3)
-    token_based_cost = math.ceil(calc_input_msats + calc_output_msats)
+
+# ============================================================================
+# Helper Functions (ordered by call sequence in calculate_cost)
+# ============================================================================
+
+
+def parse_token_count(value: object) -> int:
+    """Parse a token count from various formats (int, float, str, bool)."""
+    if isinstance(value, bool):
+        return 0
+    if isinstance(value, int):
+        return max(0, value)
+    if isinstance(value, float):
+        return max(0, int(value))
+    if isinstance(value, str):
+        try:
+            return max(0, int(float(value)))
+        except ValueError:
+            return 0
+    return 0
+
+
+def _coerce_usd(value: object) -> float:
+    """Coerce a value to USD float, handling various formats safely."""
+    if value is None or isinstance(value, bool):
+        return 0.0
+    if not isinstance(value, (int, float, str)):
+        return 0.0
+    try:
+        return max(0.0, float(value))
+    except (TypeError, ValueError):
+        return 0.0
+
+
+def _extract_token_pair(
+    usage_data: dict, standard_field: str, alt_field: str
+) -> int:
+    """Extract token count trying two field names in order."""
+    value = parse_token_count(usage_data.get(standard_field, 0))
+    if value > 0:
+        return value
+    return parse_token_count(usage_data.get(alt_field, 0))
+
+
+def _extract_cache_tokens(usage_data: dict, input_tokens: int) -> tuple[int, int, int]:
+    """Extract cache tokens, handling OpenAI vs Anthropic formats.
+
+    Returns: (cache_read_tokens, cache_creation_tokens, adjusted_input_tokens)
+    """
+    cache_read = parse_token_count(usage_data.get("cache_read_input_tokens", 0))
+    cache_creation = parse_token_count(
+        usage_data.get("cache_creation_input_tokens", 0)
+    )
+
+    # OpenAI: cache is included in input_tokens, subtract it
+    prompt_details = usage_data.get("prompt_tokens_details")
+    if isinstance(prompt_details, dict) and not cache_read:
+        openai_cached = parse_token_count(prompt_details.get("cached_tokens", 0))
+        if openai_cached:
+            cache_read = openai_cached
+            input_tokens = max(0, input_tokens - cache_read)
+
+    return cache_read, cache_creation, input_tokens
+
+
+def _resolve_usd_cost(usage_data: dict, response_data: dict) -> float:
+    """Resolve USD cost with clear priority order.
+
+    Priority: cost_details.total_cost → total_cost → cost (in both usage and response).
+    """
+    cost_details = usage_data.get("cost_details")
+    if isinstance(cost_details, dict):
+        cost = _coerce_usd(cost_details.get("total_cost"))
+        if cost > 0:
+            return cost
+
+    for source in [usage_data, response_data]:
+        if not isinstance(source, dict):
+            continue
+        for field in ("total_cost", "cost"):
+            cost = _coerce_usd(source.get(field))
+            if cost > 0:
+                return cost
+
+    return 0.0
+
+
+def _get_pricing_rates(
+    response_data: dict,
+) -> tuple[float, float, float, float] | None:
+    """Get model-based pricing rates or None if using fixed pricing.
+
+    Returns: (input_rate, output_rate, cache_read_rate, cache_write_rate)
+    """
+    if settings.fixed_pricing:
+        return None
+
+    from ..proxy import get_model_instance
+
+    response_model = response_data.get("model", "")
+    model_obj = get_model_instance(response_model)
+
+    if not model_obj:
+        logger.error("Invalid model in response", extra={"response_model": response_model})
+        raise ValueError(f"Invalid model: {response_model}")
+
+    if not model_obj.sats_pricing:
+        logger.error(
+            "Model pricing not defined",
+            extra={"model": response_model, "model_id": response_model},
+        )
+        raise ValueError("Model pricing not defined")
+
+    try:
+        mspp = float(model_obj.sats_pricing.prompt)
+        mspc = float(model_obj.sats_pricing.completion)
+        mscr = float(model_obj.sats_pricing.input_cache_read or 0)
+        mscw = float(model_obj.sats_pricing.input_cache_write or 0)
+
+        mspp_1k = mspp * 1_000_000.0
+        mspc_1k = mspc * 1_000_000.0
+        mscr_1k = mscr * 1_000_000.0 if mscr > 0 else mspp_1k
+        mscw_1k = mscw * 1_000_000.0 if mscw > 0 else mspp_1k
+
+        logger.info(
+            "Applied model-specific pricing",
+            extra={
+                "model": response_model,
+                "input_price_msats_per_1k": mspp_1k,
+                "output_price_msats_per_1k": mspc_1k,
+                "cache_read_price_msats_per_1k": mscr_1k,
+                "cache_write_price_msats_per_1k": mscw_1k,
+            },
+        )
+        return mspp_1k, mspc_1k, mscr_1k, mscw_1k
+    except Exception as e:
+        logger.error("Invalid pricing data", extra={"error": str(e)})
+        raise ValueError("Invalid pricing data") from e
+
+
+def _calculate_from_usd_cost(
+    usd_cost: float,
+    input_usd: float,
+    output_usd: float,
+    input_tokens: int,
+    cache_read_tokens: int,
+    cache_creation_tokens: int,
+    output_tokens: int,
+    response_data: dict,
+) -> CostData:
+    """Calculate cost from USD figures, deriving input/output split from tokens."""
+    sats_per_usd = 1.0 / sats_usd_price()
+    cost_in_sats = usd_cost * sats_per_usd
+    cost_in_msats = math.ceil(cost_in_sats * 1000)
+
+    if input_usd > 0 or output_usd > 0:
+        input_msats = int((input_usd * sats_per_usd) * 1000)
+        output_msats = int((output_usd * sats_per_usd) * 1000)
+    else:
+        effective_input_tokens = (
+            input_tokens + cache_read_tokens + cache_creation_tokens
+        )
+        total_tokens = effective_input_tokens + output_tokens
+        input_msats = (
+            int(cost_in_msats * effective_input_tokens / total_tokens)
+            if total_tokens > 0
+            else 0
+        )
+        output_msats = cost_in_msats - input_msats
+
+    logger.info(
+        "Using cost from usage data/details",
+        extra={
+            "usd_cost": usd_cost,
+            "cost_in_sats": cost_in_sats,
+            "cost_in_msats": cost_in_msats,
+            "model": response_data.get("model", "unknown"),
+        },
+    )
+
+    return CostData(
+        base_msats=0,
+        input_msats=input_msats,
+        output_msats=output_msats,
+        total_msats=cost_in_msats,
+        total_usd=usd_cost,
+        input_tokens=input_tokens,
+        output_tokens=output_tokens,
+        cache_read_input_tokens=cache_read_tokens,
+        cache_creation_input_tokens=cache_creation_tokens,
+        cache_read_msats=0,
+        cache_creation_msats=0,
+    )
+
+
+def _calculate_from_tokens(
+    input_tokens: int,
+    output_tokens: int,
+    cache_read_tokens: int,
+    cache_creation_tokens: int,
+    input_rate: float,
+    output_rate: float,
+    cache_read_rate: float,
+    cache_creation_rate: float,
+    response_data: dict,
+) -> CostData:
+    """Calculate cost from token counts using pricing rates."""
+    calc_input_msats = round(input_tokens / 1000 * input_rate, 3)
+    calc_output_msats = round(output_tokens / 1000 * output_rate, 3)
+    calc_cache_read_msats = round(cache_read_tokens / 1000 * cache_read_rate, 3)
+    calc_cache_write_msats = round(
+        cache_creation_tokens / 1000 * cache_creation_rate, 3
+    )
+    token_based_cost = math.ceil(
+        calc_input_msats
+        + calc_output_msats
+        + calc_cache_read_msats
+        + calc_cache_write_msats
+    )
     total_usd = (token_based_cost / 1000.0) * sats_usd_price()
 
     logger.info(
@@ -306,8 +422,12 @@ async def calculate_cost(  # todo: can be sync
         extra={
             "input_tokens": input_tokens,
             "output_tokens": output_tokens,
+            "cache_read_input_tokens": cache_read_tokens,
+            "cache_creation_input_tokens": cache_creation_tokens,
             "input_cost_msats": calc_input_msats,
             "output_cost_msats": calc_output_msats,
+            "cache_read_cost_msats": calc_cache_read_msats,
+            "cache_creation_cost_msats": calc_cache_write_msats,
             "total_cost_msats": token_based_cost,
             "total_usd": total_usd,
             "model": response_data.get("model", "unknown"),
@@ -322,4 +442,8 @@ async def calculate_cost(  # todo: can be sync
         total_usd=total_usd,
         input_tokens=input_tokens,
         output_tokens=output_tokens,
+        cache_read_input_tokens=cache_read_tokens,
+        cache_creation_input_tokens=cache_creation_tokens,
+        cache_read_msats=int(calc_cache_read_msats),
+        cache_creation_msats=int(calc_cache_write_msats),
     )

routstr/payment/models.py

@@ -363,7 +363,7 @@ async def _update_sats_pricing_once() -> None:
             for m in upstream.get_cached_models()
         ]
         upstream._models_cache = updated_models
-        upstream._models_by_id = {m.id: m for m in updated_models}
+        upstream._models_by_id = {m.forwarded_model_id or m.id: m for m in updated_models}
         updated_count += len(updated_models)
 
     if updated_count > 0:

routstr/proxy.py

@@ -17,6 +17,7 @@ from .core.db import (
     get_session,
 )
 from .core.exceptions import UpstreamError
+from .core.not_found import build_not_found_response
 from .core.settings import settings
 from .payment.helpers import (
     calculate_discounted_max_cost,
@@ -150,10 +151,31 @@ async def refresh_model_maps_periodically() -> None:
             )
 
 
+_API_PATH_PREFIXES = (
+    "v1/",
+    "responses",
+    "chat/",
+    "completions",
+    "models",
+    "embeddings",
+    "audio/",
+    "images/",
+    "moderations",
+    "providers",
+)
+
+
 @proxy_router.api_route("/{path:path}", methods=["GET", "POST"], response_model=None)
 async def proxy(
     request: Request, path: str, session: AsyncSession = Depends(get_session)
 ) -> Response | StreamingResponse:
+    # GET requests must hit a known API prefix; otherwise return a 404 (HTML
+    # for browsers, JSON for API clients). POST requests are always forwarded
+    # so that OpenAI-style endpoints work with or without the `v1/` prefix
+    # (e.g. `/chat/completions` as well as `/v1/chat/completions`).
+    if request.method == "GET" and not path.startswith(_API_PATH_PREFIXES):
+        return build_not_found_response(request, path)
+
     headers = dict(request.headers)
 
     is_responses_api = path.startswith("v1/responses") or path.startswith("responses")
@@ -210,7 +232,15 @@ async def proxy(
                     )
             except UpstreamError as e:
                 logger.warning(
-                    f"Upstream {upstream.provider_type} failed (x-cashu): {e}"
+                    "Upstream %s failed (x-cashu) for model=%s: %s",
+                    upstream.provider_type,
+                    model_id,
+                    e,
+                    extra={
+                        "provider": upstream.provider_type,
+                        "model": model_id,
+                        "status_code": e.status_code,
+                    },
                 )
                 if i == len(upstreams) - 1:
                     last_error = e
@@ -355,10 +385,14 @@ async def proxy(
                     )
 
                     logger.warning(
-                        f"Upstream {upstream.provider_type} returned {response.status_code}, trying next provider",
+                        "Upstream %s returned %s for model=%s, trying next provider",
+                        upstream.provider_type,
+                        response.status_code,
+                        model_id,
                         extra={
                             "status_code": response.status_code,
-                            "upstream": upstream.provider_type,
+                            "provider": upstream.provider_type,
+                            "model": model_id,
                         },
                     )
                     continue
@@ -366,16 +400,20 @@ async def proxy(
                 # 4xx error (user error), or other non-retryable error, or last provider failed
                 await revert_pay_for_request(key, session, max_cost_for_model)
                 logger.warning(
-                    "Upstream request failed, revert payment",
+                    "Upstream request failed, revert payment "
+                    "(provider=%s model=%s status=%s path=%s)",
+                    upstream.provider_type,
+                    model_id,
+                    response.status_code,
+                    path,
                     extra={
                         "status_code": response.status_code,
                         "path": path,
+                        "provider": upstream.provider_type,
+                        "model": model_id,
                         "key_hash": key.hashed_key[:8] + "...",
                         "key_balance": key.balance,
                         "max_cost_for_model": max_cost_for_model,
-                        "upstream_headers": response.headers
-                        if hasattr(response, "headers")
-                        else None,
                     },
                 )
                 return response
@@ -384,8 +422,16 @@ async def proxy(
 
         except UpstreamError as e:
             logger.warning(
-                f"Upstream {upstream.provider_type} failed: {e}",
-                extra={"retry": i < len(upstreams) - 1},
+                "Upstream %s failed for model=%s: %s",
+                upstream.provider_type,
+                model_id,
+                e,
+                extra={
+                    "provider": upstream.provider_type,
+                    "model": model_id,
+                    "status_code": e.status_code,
+                    "retry": i < len(upstreams) - 1,
+                },
             )
 
             # If this was the last provider

routstr/upstream/base.py

@@ -42,11 +42,23 @@ from ..payment.models import (
 from ..payment.price import sats_usd_price
 from ..wallet import recieve_token, send_token
 from . import messages_dispatch
+from .count_tokens import count_tokens_locally
 from .litellm_routing import detect_litellm_prefix
 
 logger = get_logger(__name__)
 
 
+def _is_json_content_type(content_type: str | None) -> bool:
+    """Return True when the upstream response should be parsed as JSON.
+    """
+    if not content_type:
+        return False
+    main = content_type.split(";", 1)[0].strip().lower()
+    if main in ("application/json", "text/json"):
+        return True
+    return main.startswith("application/") and main.endswith("+json")
+
+
 class TopupData(BaseModel):
     """Universal top-up data schema for Lightning Network invoices."""
 
@@ -140,6 +152,51 @@ class BaseUpstreamProvider:
             "can_show_balance": False,
         }
 
+    @staticmethod
+    def _fold_cache_into_input_tokens(usage: object) -> None:
+        """Fold cache token counts into ``input_tokens`` / ``prompt_tokens``.
+
+        Cost calculation has already used the per-bucket counts to bill the
+        request correctly; what the client sees in the visible token total
+        should be a single rolled-up prompt count *including* the cache
+        portion. The standalone ``cache_read_input_tokens`` /
+        ``cache_creation_input_tokens`` fields are left in place for clients
+        that want the breakdown.
+
+        For Anthropic-shaped responses (``input_tokens`` present), the cache
+        fields are forced to ``0`` when the upstream omitted them, so the
+        client always sees a consistent shape.
+        """
+        if not isinstance(usage, dict):
+            return
+
+        # Normalise missing cache fields to 0 on Anthropic-shaped usage so
+        # downstream consumers can rely on them being present.
+        if "input_tokens" in usage:
+            usage.setdefault("cache_read_input_tokens", 0)
+            usage.setdefault("cache_creation_input_tokens", 0)
+
+        try:
+            cache_read = int(usage.get("cache_read_input_tokens") or 0)
+            cache_creation = int(usage.get("cache_creation_input_tokens") or 0)
+        except (TypeError, ValueError):
+            return
+        extra = cache_read + cache_creation
+        if extra <= 0:
+            return
+        if "input_tokens" in usage:
+            try:
+                usage["input_tokens"] = int(usage.get("input_tokens") or 0) + extra
+            except (TypeError, ValueError):
+                pass
+        if "prompt_tokens" in usage:
+            try:
+                usage["prompt_tokens"] = (
+                    int(usage.get("prompt_tokens") or 0) + extra
+                )
+            except (TypeError, ValueError):
+                pass
+
     def inject_cost_metadata(
         self,
         response_json: dict,
@@ -163,6 +220,7 @@ class BaseUpstreamProvider:
             response_json["usage"]["cost"] = total_usd
             response_json["usage"]["cost_sats"] = sats_cost
             response_json["usage"]["remaining_balance_msats"] = key.balance
+            self._fold_cache_into_input_tokens(response_json["usage"])
 
         # Inject into Anthropic nested usage block if present
         if (
@@ -171,6 +229,7 @@ class BaseUpstreamProvider:
             and "usage" in response_json["message"]
         ):
             response_json["message"]["usage"]["sats_cost"] = sats_cost
+            self._fold_cache_into_input_tokens(response_json["message"]["usage"])
 
         # Unified Routstr metadata
         response_json["metadata"] = response_json.get("metadata", {})
@@ -474,9 +533,13 @@ class BaseUpstreamProvider:
         pass
 
     async def forward_upstream_error_response(
-        self, request: Request, path: str, upstream_response: httpx.Response
+        self,
+        request: Request,
+        path: str,
+        upstream_response: httpx.Response,
+        model_id: str | None = None,
     ) -> Response:
-        """Log upstream errors and forward the upstream response unchanged."""
+        """Log upstream errors and forward the response in a JSON envelope."""
         status_code = upstream_response.status_code
         headers = dict(upstream_response.headers)
         content_type = headers.get("content-type") or headers.get("Content-Type", "")
@@ -498,12 +561,19 @@ class BaseUpstreamProvider:
 
         message, upstream_code = self._extract_upstream_error_message(body_bytes)
         body_preview = body_bytes.decode("utf-8", errors="ignore").strip()[:500]
+        is_json_body = _is_json_content_type(content_type)
 
         logger.warning(
-            "Forwarding upstream error response as-is",
+            "Upstream %s returned %s for model=%s path=%s: %s",
+            self.provider_type,
+            status_code,
+            model_id or "unknown",
+            path,
+            (message or body_preview or "<empty>")[:300],
             extra={
                 "path": path,
                 "provider": self.provider_type,
+                "model": model_id or "unknown",
                 "upstream_status": status_code,
                 "upstream_code": upstream_code,
                 "upstream_content_type": content_type,
@@ -512,6 +582,7 @@ class BaseUpstreamProvider:
                 "body_preview": body_preview,
                 "body_read_error": body_read_error,
                 "method": request.method,
+                "json_normalized": not is_json_body,
             },
         )
 
@@ -539,17 +610,40 @@ class BaseUpstreamProvider:
         ):
             headers.pop(header_name, None)
 
-        if not content_type:
-            headers.pop("content-type", None)
-            headers.pop("Content-Type", None)
+        if is_json_body:
+            if not content_type:
+                headers.pop("content-type", None)
+                headers.pop("Content-Type", None)
+            media_type = content_type or None
+            return Response(
+                content=body_bytes,
+                status_code=status_code,
+                headers=headers,
+                media_type=media_type,
+            )
 
-        media_type = content_type or None
+        # Non-JSON upstream error (HTML, plain text, empty, ...). Wrap it in
+        # the standard JSON envelope so callers don't need a second parser.
+        for header_name in ("content-type", "Content-Type"):
+            headers.pop(header_name, None)
+
+        envelope = {
+            "error": {
+                "message": message or "Upstream returned a non-JSON error response",
+                "type": "upstream_error",
+                "code": upstream_code or status_code,
+                "upstream_status": status_code,
+                "upstream_content_type": content_type or None,
+                "upstream_body_preview": body_preview or None,
+            },
+            "request_id": getattr(request.state, "request_id", None),
+        }
 
         return Response(
-            content=body_bytes,
+            content=json.dumps(envelope).encode(),
             status_code=status_code,
             headers=headers,
-            media_type=media_type,
+            media_type="application/json",
         )
 
     async def handle_streaming_chat_completion(
@@ -570,7 +664,7 @@ class BaseUpstreamProvider:
         Returns:
             StreamingResponse with cost data injected at the end
         """
-        logger.info(
+        logger.debug(
             "Processing streaming chat completion",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
@@ -782,7 +876,7 @@ class BaseUpstreamProvider:
         Returns:
             Response with cost data added to JSON body
         """
-        logger.info(
+        logger.debug(
             "Processing non-streaming chat completion",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
@@ -826,6 +920,7 @@ class BaseUpstreamProvider:
                 response_json["usage"]["remaining_balance_msats"] = (
                     remaining_balance_msats
                 )
+                self._fold_cache_into_input_tokens(response_json["usage"])
 
             # Keep detailed cost
             response_json["metadata"] = response_json.get("metadata", {})
@@ -840,7 +935,7 @@ class BaseUpstreamProvider:
             response_json["cost"]["sats_cost"] = cost_data.get("total_msats", 0) // 1000
             response_json["cost"]["remaining_balance_msats"] = remaining_balance_msats
 
-            logger.info(
+            logger.debug(
                 "Payment adjustment completed for non-streaming",
                 extra={
                     "key_hash": key.hashed_key[:8] + "...",
@@ -917,7 +1012,7 @@ class BaseUpstreamProvider:
         Returns:
             StreamingResponse with cost data injected at the end
         """
-        logger.info(
+        logger.debug(
             "Processing streaming Responses API completion",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
@@ -1153,7 +1248,7 @@ class BaseUpstreamProvider:
         Returns:
             Response with cost data added to JSON body
         """
-        logger.info(
+        logger.debug(
             "Processing non-streaming Responses API completion",
             extra={
                 "key_hash": key.hashed_key[:8] + "...",
@@ -1200,6 +1295,7 @@ class BaseUpstreamProvider:
                 response_json["usage"]["remaining_balance_msats"] = (
                     remaining_balance_msats
                 )
+                self._fold_cache_into_input_tokens(response_json["usage"])
 
             # Keep detailed cost
             response_json["metadata"] = response_json.get("metadata", {})
@@ -1214,7 +1310,7 @@ class BaseUpstreamProvider:
             response_json["cost"]["sats_cost"] = cost_data.get("total_msats", 0) // 1000
             response_json["cost"]["remaining_balance_msats"] = remaining_balance_msats
 
-            logger.info(
+            logger.debug(
                 "Payment adjustment completed for non-streaming Responses API",
                 extra={
                     "key_hash": key.hashed_key[:8] + "...",
@@ -1295,7 +1391,7 @@ class BaseUpstreamProvider:
                     session,
                     max_cost,
                 )
-                logger.info(
+                logger.debug(
                     "Finalized generic streaming payment in background",
                     extra={
                         "path": path,
@@ -1327,6 +1423,42 @@ class BaseUpstreamProvider:
             last_model_seen: str | None = None
             input_tokens: int = 0
             output_tokens: int = 0
+            cache_read_input_tokens: int = 0
+            cache_creation_input_tokens: int = 0
+            total_cost: float = 0.0
+            input_cost: float = 0.0
+            output_cost: float = 0.0
+
+            def _coerce_usd(value: object) -> float:
+                if value is None or isinstance(value, bool):
+                    return 0.0
+                if not isinstance(value, (int, float, str)):
+                    return 0.0
+                try:
+                    return max(0.0, float(value))
+                except (TypeError, ValueError):
+                    return 0.0
+
+            def _absorb_usd(usage_or_root: dict) -> None:
+                nonlocal total_cost, input_cost, output_cost
+                cd = usage_or_root.get("cost_details")
+                if isinstance(cd, dict):
+                    total_cost = max(
+                        total_cost,
+                        _coerce_usd(cd.get("total_cost")),
+                    )
+                    input_cost = max(
+                        input_cost,
+                        _coerce_usd(cd.get("input_cost")),
+                    )
+                    output_cost = max(
+                        output_cost,
+                        _coerce_usd(cd.get("output_cost")),
+                    )
+                for field in ("total_cost", "cost"):
+                    total_cost = max(
+                        total_cost, _coerce_usd(usage_or_root.get(field))
+                    )
 
             async def finalize_without_usage() -> bytes | None:
                 nonlocal usage_finalized
@@ -1386,12 +1518,63 @@ class BaseUpstreamProvider:
                                             output_tokens += usage.get(
                                                 "output_tokens", 0
                                             )
+                                            # Anthropic's `message_start.usage`
+                                            # carries the cumulative cache
+                                            # snapshot for the prompt — pick
+                                            # the max() so subsequent
+                                            # `message_delta.usage` events
+                                            # (which only restate the same
+                                            # numbers) don't double-count.
+                                            cache_read_input_tokens = max(
+                                                cache_read_input_tokens,
+                                                int(
+                                                    usage.get(
+                                                        "cache_read_input_tokens", 0
+                                                    )
+                                                    or 0
+                                                ),
+                                            )
+                                            cache_creation_input_tokens = max(
+                                                cache_creation_input_tokens,
+                                                int(
+                                                    usage.get(
+                                                        "cache_creation_input_tokens",
+                                                        0,
+                                                    )
+                                                    or 0
+                                                ),
+                                            )
+                                            _absorb_usd(usage)
 
                                         if usage := data.get("usage"):
                                             input_tokens += usage.get("input_tokens", 0)
                                             output_tokens += usage.get(
                                                 "output_tokens", 0
                                             )
+                                            cache_read_input_tokens = max(
+                                                cache_read_input_tokens,
+                                                int(
+                                                    usage.get(
+                                                        "cache_read_input_tokens", 0
+                                                    )
+                                                    or 0
+                                                ),
+                                            )
+                                            cache_creation_input_tokens = max(
+                                                cache_creation_input_tokens,
+                                                int(
+                                                    usage.get(
+                                                        "cache_creation_input_tokens",
+                                                        0,
+                                                    )
+                                                    or 0
+                                                ),
+                                            )
+                                            _absorb_usd(usage)
+                                        # Some upstreams attach cost fields at
+                                        # the event root rather than nested
+                                        # under `usage`.
+                                        _absorb_usd(data)
                                 except json.JSONDecodeError:
                                     pass
                             modified_lines.append(line)
@@ -1406,9 +1589,23 @@ class BaseUpstreamProvider:
                 usage_data = {
                     "input_tokens": input_tokens,
                     "output_tokens": output_tokens,
+                    "cache_read_input_tokens": cache_read_input_tokens,
+                    "cache_creation_input_tokens": cache_creation_input_tokens,
                 }
+                messages_dispatch.embed_usd_costs(
+                    usage_data,
+                    total_cost,
+                    input_cost,
+                    output_cost,
+                )
 
-                if input_tokens > 0 or output_tokens > 0:
+                if (
+                    input_tokens > 0
+                    or output_tokens > 0
+                    or cache_read_input_tokens > 0
+                    or cache_creation_input_tokens > 0
+                    or total_cost > 0
+                ):
                     async with create_session() as new_session:
                         fresh_key = await new_session.get(key.__class__, key.hashed_key)
                         if fresh_key:
@@ -1645,6 +1842,7 @@ class BaseUpstreamProvider:
             response_json["usage"], dict
         ):
             response_json["usage"]["cost_sats"] = cost_data.total_msats // 1000
+            self._fold_cache_into_input_tokens(response_json["usage"])
 
         response_headers: dict[str, str] = {}
         if cost_data:
@@ -1693,6 +1891,11 @@ class BaseUpstreamProvider:
             last_model_seen: str | None = None
             input_tokens = 0
             output_tokens = 0
+            cache_read_input_tokens = 0
+            cache_creation_input_tokens = 0
+            total_cost = 0.0
+            input_cost = 0.0
+            output_cost = 0.0
 
             async def finalize_without_usage() -> bytes | None:
                 nonlocal usage_finalized
@@ -1751,21 +1954,51 @@ class BaseUpstreamProvider:
                     # double-count.
                     input_tokens = max(input_tokens, annotated.input_tokens)
                     output_tokens = max(output_tokens, annotated.output_tokens)
+                    cache_read_input_tokens = max(
+                        cache_read_input_tokens,
+                        annotated.cache_read_input_tokens,
+                    )
+                    cache_creation_input_tokens = max(
+                        cache_creation_input_tokens,
+                        annotated.cache_creation_input_tokens,
+                    )
+                    total_cost = max(total_cost, annotated.total_cost)
+                    input_cost = max(input_cost, annotated.input_cost)
+                    output_cost = max(output_cost, annotated.output_cost)
                     yield annotated.sse_bytes
 
-                if input_tokens > 0 or output_tokens > 0:
+                if (
+                    input_tokens > 0
+                    or output_tokens > 0
+                    or cache_read_input_tokens > 0
+                    or cache_creation_input_tokens > 0
+                    or total_cost > 0
+                ):
                     async with create_session() as new_session:
                         fresh_key = await new_session.get(
                             key.__class__, key.hashed_key
                         )
                         if fresh_key:
                             try:
+                                rebuilt_usage: dict = {
+                                    "input_tokens": input_tokens,
+                                    "output_tokens": output_tokens,
+                                    "cache_read_input_tokens": (
+                                        cache_read_input_tokens
+                                    ),
+                                    "cache_creation_input_tokens": (
+                                        cache_creation_input_tokens
+                                    ),
+                                }
+                                messages_dispatch.embed_usd_costs(
+                                    rebuilt_usage,
+                                    total_cost,
+                                    input_cost,
+                                    output_cost,
+                                )
                                 combined_data: dict = {
                                     "model": last_model_seen or "unknown",
-                                    "usage": {
-                                        "input_tokens": input_tokens,
-                                        "output_tokens": output_tokens,
-                                    },
+                                    "usage": rebuilt_usage,
                                 }
                                 cost_data = await adjust_payment_for_tokens(
                                     fresh_key,
@@ -1828,6 +2061,11 @@ class BaseUpstreamProvider:
         last_model_seen: str | None = None
         input_tokens = 0
         output_tokens = 0
+        cache_read_input_tokens = 0
+        cache_creation_input_tokens = 0
+        total_cost = 0.0
+        input_cost = 0.0
+        output_cost = 0.0
 
         async for annotated in messages_dispatch.stream_annotated_events(
             iterator, requested_model
@@ -1837,6 +2075,16 @@ class BaseUpstreamProvider:
             # See _stream_litellm_messages for why this is max() not +=.
             input_tokens = max(input_tokens, annotated.input_tokens)
             output_tokens = max(output_tokens, annotated.output_tokens)
+            cache_read_input_tokens = max(
+                cache_read_input_tokens, annotated.cache_read_input_tokens
+            )
+            cache_creation_input_tokens = max(
+                cache_creation_input_tokens,
+                annotated.cache_creation_input_tokens,
+            )
+            total_cost = max(total_cost, annotated.total_cost)
+            input_cost = max(input_cost, annotated.input_cost)
+            output_cost = max(output_cost, annotated.output_cost)
             buffered.append(annotated.sse_bytes)
 
         response_headers: dict[str, str] = {
@@ -1844,7 +2092,13 @@ class BaseUpstreamProvider:
             "Connection": "keep-alive",
         }
 
-        if input_tokens == 0 and output_tokens == 0:
+        if (
+            input_tokens == 0
+            and output_tokens == 0
+            and cache_read_input_tokens == 0
+            and cache_creation_input_tokens == 0
+            and total_cost == 0
+        ):
             logger.warning(
                 "x-cashu /v1/messages stream finished with no usage data "
                 "— refund cannot be computed and the client effectively "
@@ -1858,13 +2112,25 @@ class BaseUpstreamProvider:
                 },
             )
 
-        if input_tokens > 0 or output_tokens > 0:
+        if (
+            input_tokens > 0
+            or output_tokens > 0
+            or cache_read_input_tokens > 0
+            or cache_creation_input_tokens > 0
+            or total_cost > 0
+        ):
+            rebuilt_usage: dict = {
+                "input_tokens": input_tokens,
+                "output_tokens": output_tokens,
+                "cache_read_input_tokens": cache_read_input_tokens,
+                "cache_creation_input_tokens": cache_creation_input_tokens,
+            }
+            messages_dispatch.embed_usd_costs(
+                rebuilt_usage, total_cost, input_cost, output_cost
+            )
             response_data: dict = {
                 "model": last_model_seen or "unknown",
-                "usage": {
-                    "input_tokens": input_tokens,
-                    "output_tokens": output_tokens,
-                },
+                "usage": rebuilt_usage,
             }
             try:
                 cost_data = await self.get_x_cashu_cost(
@@ -1940,6 +2206,12 @@ class BaseUpstreamProvider:
         """
         path = self.normalize_request_path(path, model_obj)
 
+        if (
+            path.endswith("messages/count_tokens")
+            and not self.supports_anthropic_messages
+        ):
+            return count_tokens_locally(request_body, model_obj)
+
         if (
             path.endswith("messages")
             and not path.endswith("count_tokens")
@@ -1961,15 +2233,15 @@ class BaseUpstreamProvider:
 
         transformed_body = self.prepare_request_body(request_body, model_obj)
 
-        logger.info(
+        logger.debug(
             "Forwarding request to upstream",
             extra={
                 "url": url,
                 "method": request.method,
                 "path": path,
+                "model": original_model_id or "unknown",
+                "provider": self.provider_type,
                 "key_hash": key.hashed_key[:8] + "...",
-                "key_balance": key.balance,
-                "has_request_body": request_body is not None,
             },
         )
 
@@ -2002,41 +2274,43 @@ class BaseUpstreamProvider:
                     stream=True,
                 )
 
-            if response.status_code != 200:
-                logger.error(
-                    "Received upstream response",
-                    extra={
-                        "reason_phrase": response.reason_phrase,
-                        "status_code": response.status_code,
-                        "path": path,
-                        "key_hash": key.hashed_key[:8] + "...",
-                        "content_type": response.headers.get("content-type", "unknown"),
-                    },
-                )
-            else:
-                logger.info(
-                    "Received upstream response",
-                    extra={
-                        "reason_phrase": response.reason_phrase,
-                        "status_code": response.status_code,
-                        "path": path,
-                        "key_hash": key.hashed_key[:8] + "...",
-                        "content_type": response.headers.get("content-type", "unknown"),
-                    },
-                )
-
             if response.status_code != 200:
                 if response.status_code >= 500:
+                    try:
+                        body_bytes = await response.aread()
+                    except Exception:
+                        body_bytes = b""
+                    body_preview = body_bytes.decode(
+                        "utf-8", errors="ignore"
+                    ).strip()[:500]
+                    logger.error(
+                        "Upstream %s returned %s for model=%s path=%s: %s",
+                        self.provider_type,
+                        response.status_code,
+                        original_model_id or "unknown",
+                        path,
+                        body_preview or "<empty>",
+                        extra={
+                            "provider": self.provider_type,
+                            "model": original_model_id or "unknown",
+                            "status_code": response.status_code,
+                            "reason_phrase": response.reason_phrase,
+                            "path": path,
+                            "body_preview": body_preview,
+                        },
+                    )
                     await response.aclose()
                     await client.aclose()
                     raise UpstreamError(
-                        f"Upstream returned status {response.status_code}",
+                        f"Upstream {self.provider_type} returned {response.status_code} "
+                        f"for model {original_model_id or 'unknown'}: "
+                        f"{body_preview[:200] or '<empty>'}",
                         status_code=response.status_code,
                     )
 
                 try:
                     mapped_error = await self.forward_upstream_error_response(
-                        request, path, response
+                        request, path, response, model_id=original_model_id
                     )
                 finally:
                     await response.aclose()
@@ -2281,15 +2555,15 @@ class BaseUpstreamProvider:
 
         transformed_body = self.prepare_responses_request_body(request_body, model_obj)
 
-        logger.info(
+        logger.debug(
             "Forwarding Responses API request to upstream",
             extra={
                 "url": url,
                 "method": request.method,
                 "path": path,
+                "model": original_model_id or "unknown",
+                "provider": self.provider_type,
                 "key_hash": key.hashed_key[:8] + "...",
-                "key_balance": key.balance,
-                "has_request_body": request_body is not None,
             },
         )
 
@@ -2322,28 +2596,42 @@ class BaseUpstreamProvider:
                     stream=True,
                 )
 
-            logger.info(
-                "Received upstream Responses API response",
-                extra={
-                    "status_code": response.status_code,
-                    "path": path,
-                    "key_hash": key.hashed_key[:8] + "...",
-                    "content_type": response.headers.get("content-type", "unknown"),
-                },
-            )
-
             if response.status_code != 200:
                 if response.status_code >= 500:
+                    try:
+                        body_bytes = await response.aread()
+                    except Exception:
+                        body_bytes = b""
+                    body_preview = body_bytes.decode(
+                        "utf-8", errors="ignore"
+                    ).strip()[:500]
+                    logger.error(
+                        "Upstream %s returned %s for model=%s path=%s: %s",
+                        self.provider_type,
+                        response.status_code,
+                        original_model_id or "unknown",
+                        path,
+                        body_preview or "<empty>",
+                        extra={
+                            "provider": self.provider_type,
+                            "model": original_model_id or "unknown",
+                            "status_code": response.status_code,
+                            "path": path,
+                            "body_preview": body_preview,
+                        },
+                    )
                     await response.aclose()
                     await client.aclose()
                     raise UpstreamError(
-                        f"Upstream returned status {response.status_code}",
+                        f"Upstream {self.provider_type} returned {response.status_code} "
+                        f"for model {original_model_id or 'unknown'}: "
+                        f"{body_preview[:200] or '<empty>'}",
                         status_code=response.status_code,
                     )
 
                 try:
                     mapped_error = await self.forward_upstream_error_response(
-                        request, path, response
+                        request, path, response, model_id=original_model_id
                     )
                 finally:
                     await response.aclose()
@@ -2488,9 +2776,14 @@ class BaseUpstreamProvider:
         path = self.normalize_request_path(path)
         url = self.build_request_url(path)
 
-        logger.info(
+        logger.debug(
             "Forwarding GET request to upstream",
-            extra={"url": url, "method": request.method, "path": path},
+            extra={
+                "url": url,
+                "method": request.method,
+                "path": path,
+                "provider": self.provider_type,
+            },
         )
 
         async with httpx.AsyncClient(
@@ -2508,9 +2801,13 @@ class BaseUpstreamProvider:
                     ),
                 )
 
-                logger.info(
-                    "GET request forwarded successfully",
-                    extra={"path": path, "status_code": response.status_code},
+                logger.debug(
+                    "GET request forwarded",
+                    extra={
+                        "path": path,
+                        "status_code": response.status_code,
+                        "provider": self.provider_type,
+                    },
                 )
                 if response.status_code != 200:
                     try:
@@ -2797,7 +3094,7 @@ class BaseUpstreamProvider:
                         raise ValueError(f"Invalid unit: {unit}")
 
                     if refund_amount > 0:
-                        logger.info(
+                        logger.debug(
                             "Processing refund for streaming response",
                             extra={
                                 "original_amount": amount,
@@ -2944,7 +3241,7 @@ class BaseUpstreamProvider:
             else:
                 raise ValueError(f"Invalid unit: {unit}")
 
-            logger.info(
+            logger.debug(
                 "Processing non-streaming response cost calculation",
                 extra={
                     "original_amount": amount,
@@ -3138,6 +3435,12 @@ class BaseUpstreamProvider:
 
         request_body = await request.body()
 
+        if (
+            path.endswith("messages/count_tokens")
+            and not self.supports_anthropic_messages
+        ):
+            return count_tokens_locally(request_body, model_obj)
+
         if (
             path.endswith("messages")
             and not path.endswith("count_tokens")
@@ -3334,7 +3637,7 @@ class BaseUpstreamProvider:
         Returns:
             Response or StreamingResponse from upstream with refund if applicable
         """
-        logger.info(
+        logger.debug(
             "Processing X-Cashu payment for Responses API",
             extra={
                 "path": path,
@@ -3766,7 +4069,7 @@ class BaseUpstreamProvider:
                         raise ValueError(f"Invalid unit: {unit}")
 
                     if refund_amount > 0:
-                        logger.info(
+                        logger.debug(
                             "Processing refund for streaming Responses API response",
                             extra={
                                 "original_amount": amount,
@@ -3902,7 +4205,7 @@ class BaseUpstreamProvider:
             else:
                 raise ValueError(f"Invalid unit: {unit}")
 
-            logger.info(
+            logger.debug(
                 "Processing non-streaming Responses API cost calculation",
                 extra={
                     "original_amount": amount,
@@ -4003,7 +4306,7 @@ class BaseUpstreamProvider:
         Returns:
             Response or StreamingResponse from upstream with refund if applicable
         """
-        logger.info(
+        logger.debug(
             "Processing X-Cashu payment request",
             extra={
                 "path": path,
@@ -4305,7 +4608,7 @@ class BaseUpstreamProvider:
                 except Exception:
                     self._models_cache = models_with_fees
 
-                self._models_by_id = {m.id: m for m in self._models_cache}
+                self._models_by_id = {m.forwarded_model_id or m.id: m for m in self._models_cache}
 
         except Exception as e:
             logger.error(

routstr/upstream/count_tokens.py

@@ -0,0 +1,108 @@
+"""Local handling of Anthropic ``/v1/messages/count_tokens`` for upstreams
+that do not natively expose the endpoint.
+
+Most non-Anthropic upstreams (OpenAI-compat, Gemini OpenAI-compat,
+OpenRouter chat-completions, generic providers) return 400/404 when asked
+to ``POST /messages/count_tokens``. Claude Code and other Anthropic SDK
+clients call this endpoint before each turn to size context windows and
+trigger compaction, so a failure breaks the whole chat.
+
+We answer locally. ``litellm.token_counter`` understands the Anthropic
+message shape and the per-model tokenizers, so we prefer it. If it raises
+(unknown model, encoding lookup failure, ...), we fall back to the
+project's own ``estimate_tokens`` heuristic, which is always defined and
+never raises.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+import litellm
+from fastapi.responses import Response
+
+from ..core import get_logger
+from ..payment.helpers import estimate_tokens
+from ..payment.models import Model
+
+logger = get_logger(__name__)
+
+
+def _parse_request_body(request_body: bytes | None) -> dict[str, Any]:
+    if not request_body:
+        return {}
+    try:
+        parsed = json.loads(request_body)
+    except (ValueError, TypeError):
+        return {}
+    return parsed if isinstance(parsed, dict) else {}
+
+
+def _count_with_litellm(model: str, body: dict[str, Any]) -> int:
+    messages = body.get("messages")
+    if not isinstance(messages, list):
+        messages = []
+
+    system = body.get("system")
+    if isinstance(system, str) and system:
+        messages = [{"role": "system", "content": system}, *messages]
+    elif isinstance(system, list):
+        text = "".join(
+            block.get("text", "")
+            for block in system
+            if isinstance(block, dict) and block.get("type") == "text"
+        )
+        if text:
+            messages = [{"role": "system", "content": text}, *messages]
+
+    tools = body.get("tools") if isinstance(body.get("tools"), list) else None
+
+    return int(
+        litellm.token_counter(
+            model=model,
+            messages=messages,
+            tools=tools,
+        )
+    )
+
+
+def count_tokens_locally(
+    request_body: bytes | None,
+    model_obj: Model | None,
+) -> Response:
+    """Return an Anthropic-compatible count_tokens response without
+    touching the upstream. Always returns 200; never raises."""
+    body = _parse_request_body(request_body)
+
+    model_name = ""
+    if model_obj is not None:
+        model_name = model_obj.forwarded_model_id or model_obj.id or ""
+    if not model_name:
+        body_model = body.get("model")
+        if isinstance(body_model, str):
+            model_name = body_model
+
+    input_tokens: int
+    try:
+        input_tokens = _count_with_litellm(model_name, body)
+    except Exception as exc:
+        messages = body.get("messages")
+        fallback_messages = messages if isinstance(messages, list) else []
+        input_tokens = estimate_tokens(fallback_messages)
+        logger.debug(
+            "litellm token_counter failed; using local estimator",
+            extra={
+                "model": model_name,
+                "error": str(exc),
+                "error_type": type(exc).__name__,
+                "estimated_tokens": input_tokens,
+            },
+        )
+
+    payload = {"input_tokens": max(0, int(input_tokens))}
+    return Response(
+        content=json.dumps(payload).encode(),
+        status_code=200,
+        media_type="application/json",
+    )

routstr/upstream/messages_dispatch.py

@@ -248,12 +248,28 @@ class AnnotatedEvent(NamedTuple):
     streaming paths in ``BaseUpstreamProvider`` consume ``sse_bytes`` plus
     the tallies and only differ in whether they stream live or buffer
     first.
+
+    ``cache_read_input_tokens`` and ``cache_creation_input_tokens`` are
+    surfaced separately so the cost path can price them against the cache
+    rate rather than fold them silently into the regular input bucket.
+
+    ``total_cost`` / ``input_cost`` / ``output_cost`` carry any
+    USD cost figures the upstream attached to this event (from
+    ``usage.cost``, ``usage.total_cost``, or ``usage.cost_details``) so the
+    streaming paths can re-embed them in the rebuilt ``usage`` dict and let
+    ``calculate_cost`` convert directly USD→sats instead of falling back to
+    token-based math.
     """
 
     event: dict
     sse_bytes: bytes
     input_tokens: int
     output_tokens: int
+    cache_read_input_tokens: int
+    cache_creation_input_tokens: int
+    total_cost: float
+    input_cost: float
+    output_cost: float
     model: str | None
 
 
@@ -272,21 +288,65 @@ def annotate_event(event: dict, requested_model: str | None) -> AnnotatedEvent:
 
     in_tokens = 0
     out_tokens = 0
+    cache_read_tokens = 0
+    cache_create_tokens = 0
+    total_cost = 0.0
+    input_cost = 0.0
+    output_cost = 0.0
     model: str | None = None
 
+    def _coerce_float(value: object) -> float:
+        if value is None or isinstance(value, bool):
+            return 0.0
+        if not isinstance(value, (int, float, str)):
+            return 0.0
+        try:
+            return max(0.0, float(value))
+        except (TypeError, ValueError):
+            return 0.0
+
+    def _accumulate(usage: dict) -> None:
+        nonlocal in_tokens, out_tokens, cache_read_tokens, cache_create_tokens
+        nonlocal total_cost, input_cost, output_cost
+        in_tokens += int(usage.get("input_tokens") or 0)
+        out_tokens += int(usage.get("output_tokens") or 0)
+        cache_read_tokens += int(usage.get("cache_read_input_tokens") or 0)
+        cache_create_tokens += int(usage.get("cache_creation_input_tokens") or 0)
+        total_cost += _coerce_float(usage.get("total_cost"))
+        input_cost += _coerce_float(usage.get("input_cost"))
+        output_cost += _coerce_float(usage.get("output_cost"))
+
     msg_for_meta = event.get("message")
     if isinstance(msg_for_meta, dict):
         if msg_for_meta.get("model"):
             model = str(msg_for_meta["model"])
         usage = msg_for_meta.get("usage")
         if isinstance(usage, dict):
-            in_tokens += int(usage.get("input_tokens") or 0)
-            out_tokens += int(usage.get("output_tokens") or 0)
+            _accumulate(usage)
 
     if isinstance(event.get("usage"), dict):
-        usage = event["usage"]
-        in_tokens += int(usage.get("input_tokens") or 0)
-        out_tokens += int(usage.get("output_tokens") or 0)
+        _accumulate(event["usage"])
+
+    # Some upstreams (notably OpenRouter-style proxies) attach cost fields
+    # directly at the event root rather than inside ``usage``.
+    for field in ("total_cost", "cost"):
+        total_cost = max(total_cost, _coerce_float(event.get(field)))
+    input_cost = max(input_cost, _coerce_float(event.get("input_cost")))
+    output_cost = max(output_cost, _coerce_float(event.get("output_cost")))
+    root_cost_details = event.get("cost_details")
+    if isinstance(root_cost_details, dict):
+        total_cost = max(
+            total_cost,
+            _coerce_float(root_cost_details.get("total_cost")),
+        )
+        input_cost = max(
+            input_cost,
+            _coerce_float(root_cost_details.get("input_cost")),
+        )
+        output_cost = max(
+            output_cost,
+            _coerce_float(root_cost_details.get("output_cost")),
+        )
 
     event_type = str(event.get("type") or "")
     payload = json.dumps(event)
@@ -295,7 +355,18 @@ def annotate_event(event: dict, requested_model: str | None) -> AnnotatedEvent:
     else:
         sse_bytes = f"data: {payload}\n\n".encode()
 
-    return AnnotatedEvent(event, sse_bytes, in_tokens, out_tokens, model)
+    return AnnotatedEvent(
+        event,
+        sse_bytes,
+        in_tokens,
+        out_tokens,
+        cache_read_tokens,
+        cache_create_tokens,
+        total_cost,
+        input_cost,
+        output_cost,
+        model,
+    )
 
 
 async def stream_annotated_events(
@@ -315,6 +386,38 @@ async def stream_annotated_events(
             yield annotate_event(event, requested_model)
 
 
+def embed_usd_costs(
+    usage: dict,
+    total_cost: float,
+    input_cost: float,
+    output_cost: float,
+) -> None:
+    """Mutate ``usage`` so ``calculate_cost`` will pick up the USD totals.
+
+    Mirrors the upstream shape: when any USD figure is present, attach
+    ``cost`` (used by the simple-fallback branch in ``calculate_cost``) and
+    a ``cost_details`` block (used by the preferred branch — also gives the
+    input/output USD split when we have one).
+    """
+    if total_cost <= 0 and input_cost <= 0 and output_cost <= 0:
+        return
+
+    cost_details: dict[str, float] = {}
+    effective_total = total_cost
+    if effective_total <= 0 and (input_cost > 0 or output_cost > 0):
+        effective_total = input_cost + output_cost
+
+    if effective_total > 0:
+        cost_details["total_cost"] = effective_total
+        usage["cost"] = effective_total
+    if input_cost > 0:
+        cost_details["input_cost"] = input_cost
+    if output_cost > 0:
+        cost_details["output_cost"] = output_cost
+    if cost_details:
+        usage["cost_details"] = cost_details
+
+
 def compute_refund(amount: int, unit: str, cost_msats: int) -> int:
     if unit == "msat":
         return amount - cost_msats

routstr/upstream/ollama.py

@@ -185,7 +185,7 @@ class OllamaUpstreamProvider(BaseUpstreamProvider):
             except Exception:
                 self._models_cache = models_with_fees
 
-            self._models_by_id = {m.id: m for m in self._models_cache}
+            self._models_by_id = {m.forwarded_model_id or m.id: m for m in self._models_cache}
             logger.info(
                 f"Refreshed models cache for {self.base_url}",
                 extra={"model_count": len(models)},

routstr/upstream/routstr.py

@@ -18,6 +18,10 @@ class RoutstrUpstreamProvider(BaseUpstreamProvider):
     provider_type = "routstr"
     default_base_url = None
     platform_url = None
+    # Upstream Routstr nodes serve `/v1/messages` natively, so forward the
+    # request as-is instead of round-tripping through litellm's
+    # Anthropic→OpenAI translator.
+    supports_anthropic_messages = True
 
     def __init__(
         self,
@@ -43,6 +47,13 @@ class RoutstrUpstreamProvider(BaseUpstreamProvider):
         )
         self.settings = provider_settings or {}
 
+    def normalize_request_path(
+        self, path: str, model_obj: "Model | None" = None
+    ) -> str:
+        """Preserve the ``v1/`` prefix when forwarding to an upstream Routstr.
+        """
+        return path.lstrip("/")
+
     @classmethod
     def from_db_row(
         cls, provider_row: "UpstreamProviderRow"

routstr/wallet.py

@@ -48,6 +48,8 @@ async def recieve_token(
     if token_obj.mint not in settings.cashu_mints:
         return await swap_to_primary_mint(token_obj, wallet)
 
+    await wallet.load_mint(keyset_id=token_obj.keysets[0])
+
     wallet.verify_proofs_dleq(token_obj.proofs)
     await wallet.split(proofs=token_obj.proofs, amount=0, include_fees=True)
 
@@ -56,17 +58,56 @@ async def recieve_token(
 
 async def send(amount: int, unit: str, mint_url: str | None = None) -> tuple[int, str]:
     """Internal send function - returns amount and serialized token"""
-    wallet: Wallet = await get_wallet(mint_url or settings.primary_mint, unit)
-    proofs = get_proofs_per_mint_and_unit(
-        wallet, mint_url or settings.primary_mint, unit
+    effective_mint_url = mint_url or settings.primary_mint
+    wallet: Wallet = await get_wallet(effective_mint_url, unit)
+    proofs = get_proofs_per_mint_and_unit(wallet, effective_mint_url, unit)
+    proofs_for_mint = sum(p.amount for p in proofs)
+
+    # Fallback: proofs from untrusted source mints are swapped to primary_mint
+    # during receive, so the user's preferred refund_mint_url may have no proofs
+    # even though the global wallet has the balance.
+    if proofs_for_mint < amount and effective_mint_url != settings.primary_mint:
+        logger.info(
+            f"send: insufficient proofs at {effective_mint_url} "
+            f"(have {proofs_for_mint}, need {amount}), falling back to primary_mint={settings.primary_mint}"
+        )
+        effective_mint_url = settings.primary_mint
+        wallet = await get_wallet(effective_mint_url, unit)
+        proofs = get_proofs_per_mint_and_unit(wallet, effective_mint_url, unit)
+        proofs_for_mint = sum(p.amount for p in proofs)
+
+    all_mint_urls = list({k.mint_url for k in wallet.keysets.values()})
+    proof_summary = {
+        f"{k.mint_url}/{k.unit.name}": sum(p.amount for p in wallet.proofs if p.id == k.id)
+        for k in wallet.keysets.values()
+    }
+    # Show ALL proofs in DB by keyset_id, regardless of whether the loaded wallet
+    # knows about that keyset. This reveals proofs orphaned under stale keysets.
+    raw_proofs_by_keyset: dict[str, int] = {}
+    for p in wallet.proofs:
+        raw_proofs_by_keyset[p.id] = raw_proofs_by_keyset.get(p.id, 0) + p.amount
+    logger.info(
+        f"send: proof inventory | mint={effective_mint_url} unit={unit} amount={amount} "
+        f"primary_mint={settings.primary_mint} proofs_for_mint={proofs_for_mint} "
+        f"all_mints={all_mint_urls} by_keyset={proof_summary} "
+        f"raw_proofs_by_keyset_id={raw_proofs_by_keyset} "
+        f"total_wallet_proofs={sum(p.amount for p in wallet.proofs)}"
     )
 
+    # Reserve proofs only after serialization succeeds — if serialize_proofs or
+    # swap_to_send fails mid-way, proofs stay unreserved so dashboard balance
+    # doesn't go negative.
     send_proofs, _ = await wallet.select_to_send(
-        proofs, amount, set_reserved=True, include_fees=False
-    )
-    token = await wallet.serialize_proofs(
-        send_proofs, include_dleq=False, legacy=False, memo=None
+        proofs, amount, set_reserved=False, include_fees=False
     )
+    try:
+        token = await wallet.serialize_proofs(
+            send_proofs, include_dleq=False, legacy=False, memo=None
+        )
+    except Exception:
+        await wallet.set_reserved_for_send(send_proofs, reserved=False)
+        raise
+    await wallet.set_reserved_for_send(send_proofs, reserved=True)
     return amount, token
 
 
@@ -81,10 +122,11 @@ async def _calculate_swap_amount(
     token_mint_url: str,
     token_wallet: Wallet,
     primary_wallet: Wallet,
+    proofs: list,
 ) -> int:
     """
     Calculate the amount to mint on the primary mint after accounting for
-    potential swap fees (melt fees) on the foreign mint.
+    melt fees and NUT-02 input fees on the foreign mint.
     """
     if settings.primary_mint_unit == "sat":
         receive_amount = amount_msat // 1000
@@ -111,10 +153,11 @@ async def _calculate_swap_amount(
         dummy_melt_quote = await token_wallet.melt_quote(dummy_mint_quote.request)
 
         fee_reserve = dummy_melt_quote.fee_reserve
+        input_fees = token_wallet.get_fees_for_proofs(proofs)
         if token_unit == "sat":
-            fee_msat = fee_reserve * 1000
+            fee_msat = (fee_reserve + input_fees) * 1000
         else:
-            fee_msat = fee_reserve
+            fee_msat = fee_reserve + input_fees
 
         amount_msat_after_fee = amount_msat - fee_msat
 
@@ -124,13 +167,14 @@ async def _calculate_swap_amount(
             minted_amount = int(amount_msat_after_fee)
 
         if minted_amount <= 0:
-            raise ValueError(f"Fees ({fee_reserve} {token_unit}) exceed token amount")
+            raise ValueError(f"Fees ({fee_reserve + input_fees} {token_unit}) exceed token amount")
 
         logger.info(
             "swap_to_primary_mint: fee estimation result",
             extra={
                 "token_amount_sat": amount_msat // 1000,
                 "estimated_fee_sat": fee_msat // 1000,
+                "input_fees": input_fees,
                 "minted_amount": minted_amount,
                 "minted_unit": settings.primary_mint_unit,
             },
@@ -191,6 +235,7 @@ async def swap_to_primary_mint(
         token_obj.mint,
         token_wallet,
         primary_wallet,
+        token_obj.proofs,
     )
 
     mint_quote = await primary_wallet.request_mint(minted_amount)
@@ -200,13 +245,15 @@ async def swap_to_primary_mint(
     )
 
     melt_quote = await token_wallet.melt_quote(mint_quote.request)
-    total_needed = melt_quote.amount + melt_quote.fee_reserve
+    input_fees = token_wallet.get_fees_for_proofs(token_obj.proofs)
+    total_needed = melt_quote.amount + melt_quote.fee_reserve + input_fees
     logger.info(
         "swap_to_primary_mint: melt quote received",
         extra={
             "melt_quote_id": melt_quote.quote,
             "melt_amount": melt_quote.amount,
             "melt_fee_reserve": melt_quote.fee_reserve,
+            "input_fees": input_fees,
             "total_needed": total_needed,
             "token_amount": token_amount,
         },
@@ -219,6 +266,7 @@ async def swap_to_primary_mint(
                 "token_amount": token_amount,
                 "melt_amount": melt_quote.amount,
                 "melt_fee_reserve": melt_quote.fee_reserve,
+                "input_fees": input_fees,
                 "total_needed": total_needed,
                 "shortfall": total_needed - token_amount,
             },
@@ -226,7 +274,7 @@ async def swap_to_primary_mint(
         raise ValueError(
             f"Token amount ({token_amount} {token_obj.unit}) is insufficient to cover "
             f"melt fees. Needed: {total_needed} {token_obj.unit} "
-            f"(amount: {melt_quote.amount} + fee: {melt_quote.fee_reserve})"
+            f"(amount: {melt_quote.amount} + fee: {melt_quote.fee_reserve} + input_fees: {input_fees})"
         )
 
     try:
@@ -257,19 +305,66 @@ async def swap_to_primary_mint(
         extra={"minted_amount": minted_amount, "mint_quote_id": mint_quote.quote},
     )
 
+    await primary_wallet.load_proofs(reload=True)
+    pre_mint_balance = primary_wallet.available_balance.amount
     try:
         _ = await primary_wallet.mint(minted_amount, quote_id=mint_quote.quote)
     except Exception as e:
-        logger.error(
-            "swap_to_primary_mint: mint on primary failed after successful melt",
-            extra={
-                "error": str(e),
-                "error_type": type(e).__name__,
-                "minted_amount": minted_amount,
-                "mint_quote_id": mint_quote.quote,
-            },
-        )
-        raise
+        if "11003" in str(e) or "outputs already signed" in str(e).lower():
+            # Previous mint call signed outputs at the mint but failed before
+            # bump_secret_derivation ran locally. Recover orphaned proofs and
+            # advance the counter so the next request derives fresh secrets.
+            logger.warning(
+                "swap_to_primary_mint: outputs already signed — recovering orphaned proofs",
+                extra={"mint_quote_id": mint_quote.quote, "minted_amount": minted_amount},
+            )
+            try:
+                for keyset_id in primary_wallet.keysets:
+                    await primary_wallet.restore_tokens_for_keyset(keyset_id, to=1, batch=25)
+                await primary_wallet.load_proofs(reload=True)
+                post_recovery_balance = primary_wallet.available_balance.amount
+                balance_gained = post_recovery_balance - pre_mint_balance
+                logger.info(
+                    "swap_to_primary_mint: recovery scan completed",
+                    extra={
+                        "pre_mint_balance": pre_mint_balance,
+                        "post_recovery_balance": post_recovery_balance,
+                        "balance_gained": balance_gained,
+                        "expected": minted_amount,
+                    },
+                )
+                if balance_gained < minted_amount:
+                    # Recovery scan ran but did NOT restore the orphaned proofs
+                    # (mint reports them as spent — they're stuck). Refuse to
+                    # credit the API key balance for proofs we don't actually hold.
+                    raise ValueError(
+                        f"Swap recovery failed: mint signed outputs but proofs are "
+                        f"unrecoverable (mint reports them spent). "
+                        f"Expected {minted_amount}, recovered {balance_gained}. "
+                        f"Local wallet DB ('.wallet/') state is corrupted — "
+                        f"the counter for keyset is stuck at a bad index range."
+                    )
+            except ValueError:
+                raise
+            except Exception as recovery_err:
+                logger.error(
+                    "swap_to_primary_mint: recovery failed",
+                    extra={"error": str(recovery_err)},
+                )
+                raise ValueError(
+                    f"Mint on primary failed and recovery unsuccessful: {e}"
+                ) from e
+        else:
+            logger.error(
+                "swap_to_primary_mint: mint on primary failed after successful melt",
+                extra={
+                    "error": str(e),
+                    "error_type": type(e).__name__,
+                    "minted_amount": minted_amount,
+                    "mint_quote_id": mint_quote.quote,
+                },
+            )
+            raise
 
     logger.info(
         "swap_to_primary_mint: completed successfully",
@@ -443,7 +538,7 @@ async def fetch_all_balances(
                 "unit": unit,
                 "wallet_balance": proofs_balance,
                 "user_balance": user_balance,
-                "owner_balance": proofs_balance - user_balance,
+                "owner_balance": proofs_balance - user_balance if proofs_balance != 0 else 0,
             }
             return result
         except Exception as e:
@@ -491,7 +586,9 @@ async def fetch_all_balances(
             total_wallet_balance_sats += proofs_balance_sats
             total_user_balance_sats += user_balance_sats
 
-    owner_balance = total_wallet_balance_sats - total_user_balance_sats
+    owner_balance = 0
+    if total_wallet_balance_sats != 0:
+        owner_balance = total_wallet_balance_sats - total_user_balance_sats
 
     return (
         balance_details,
@@ -502,11 +599,11 @@ async def fetch_all_balances(
 
 
 async def periodic_payout() -> None:
-    if not settings.receive_ln_address:
-        logger.warning("RECEIVE_LN_ADDRESS is not set, periodic payout disabled")
-        return
     while True:
-        await asyncio.sleep(60 * 15)
+        await asyncio.sleep(settings.payout_interval_seconds)
+        print(settings.payout_interval_seconds)
+        if not settings.receive_ln_address:
+            continue
         try:
             async with db.create_session() as session:
                 for mint_url in settings.cashu_mints:
@@ -524,7 +621,12 @@ async def periodic_payout() -> None:
                             user_balance = user_balance // 1000
                         proofs_balance = sum(proof.amount for proof in proofs)
                         available_balance = proofs_balance - user_balance
-                        min_amount = 210 if unit == "sat" else 210000
+                        # Threshold is configured in sats; convert for msat wallets.
+                        min_amount = (
+                            settings.min_payout_sat
+                            if unit == "sat"
+                            else settings.min_payout_sat * 1000
+                        )
                         if available_balance > min_amount:
                             amount_received = await raw_send_to_lnurl(
                                 wallet,

tests/integration/test_wallet_refund.py

@@ -372,17 +372,17 @@ async def test_refund_rejects_concurrent_topup_on_same_key(
     topup_amount_sat = 500
     topup_token = await testmint_wallet.mint_tokens(topup_amount_sat)
 
-    validate_called = asyncio.Event()
+    key_looked_up = asyncio.Event()
     allow_refund_to_continue = asyncio.Event()
-    original_validate_bearer_key = balance_module.validate_bearer_key
+    original_lookup = balance_module._lookup_key_no_create
     delayed_once = False
 
-    async def delayed_validate_bearer_key(*args: Any, **kwargs: Any) -> ApiKey:
+    async def delayed_lookup_key_no_create(*args: Any, **kwargs: Any) -> ApiKey | None:
         nonlocal delayed_once
-        key = await original_validate_bearer_key(*args, **kwargs)
-        if not delayed_once:
+        key = await original_lookup(*args, **kwargs)
+        if not delayed_once and key is not None:
             delayed_once = True
-            validate_called.set()
+            key_looked_up.set()
             await allow_refund_to_continue.wait()
         return key
 
@@ -390,7 +390,7 @@ async def test_refund_rejects_concurrent_topup_on_same_key(
         return await authenticated_client.post("/v1/wallet/refund")
 
     async def issue_topup() -> Any:
-        await validate_called.wait()
+        await key_looked_up.wait()
         try:
             return await authenticated_client.post(
                 "/v1/wallet/topup", params={"cashu_token": topup_token}
@@ -399,7 +399,7 @@ async def test_refund_rejects_concurrent_topup_on_same_key(
             allow_refund_to_continue.set()
 
     with patch(
-        "routstr.balance.validate_bearer_key", new=delayed_validate_bearer_key
+        "routstr.balance._lookup_key_no_create", new=delayed_lookup_key_no_create
     ):
         refund_response, topup_response = await asyncio.gather(
             issue_refund(), issue_topup()

tests/unit/test_balance.py

@@ -168,12 +168,12 @@ async def test_apikey_refund_stores_cashu_transaction_with_apikey_source() -> No
     refund_token = "cashuArefund_apikey_token"
 
     session = MagicMock()
+    session.get = AsyncMock(return_value=key)
     session.exec = AsyncMock(return_value=_update_result(1))
     session.add = MagicMock()
     session.commit = AsyncMock()
 
     with (
-        patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
         patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
         patch("routstr.balance.send_token", AsyncMock(return_value=refund_token)),
         patch("routstr.balance.store_cashu_transaction", AsyncMock()) as mock_store,
@@ -203,12 +203,12 @@ async def test_apikey_refund_logs_token() -> None:
     refund_token = "cashuAlogged_token"
 
     session = MagicMock()
+    session.get = AsyncMock(return_value=key)
     session.exec = AsyncMock(return_value=_update_result(1))
     session.add = MagicMock()
     session.commit = AsyncMock()
 
     with (
-        patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
         patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
         patch("routstr.balance.send_token", AsyncMock(return_value=refund_token)),
         patch("routstr.balance.store_cashu_transaction", AsyncMock()),
@@ -232,12 +232,12 @@ async def test_apikey_refund_log_includes_path() -> None:
     refund_token = "cashuApath_token"
 
     session = MagicMock()
+    session.get = AsyncMock(return_value=key)
     session.exec = AsyncMock(return_value=_update_result(1))
     session.add = MagicMock()
     session.commit = AsyncMock()
 
     with (
-        patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
         patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
         patch("routstr.balance.send_token", AsyncMock(return_value=refund_token)),
         patch("routstr.balance.store_cashu_transaction", AsyncMock()),
@@ -269,6 +269,7 @@ async def test_apikey_refund_rejects_on_concurrent_balance_change() -> None:
     key = _make_api_key(balance=5000, refund_currency="sat")
 
     session = MagicMock()
+    session.get = AsyncMock(return_value=key)
     # Debit returns rowcount=0 → balance changed concurrently
     session.exec = AsyncMock(return_value=_update_result(0))
     session.commit = AsyncMock()
@@ -276,7 +277,6 @@ async def test_apikey_refund_rejects_on_concurrent_balance_change() -> None:
     mock_send_token = AsyncMock(return_value="cashuAshould_not_be_minted")
 
     with (
-        patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
         patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
         patch("routstr.balance.send_token", mock_send_token),
         patch("routstr.balance.store_cashu_transaction", AsyncMock()),
@@ -333,11 +333,11 @@ async def test_apikey_refund_restores_balance_on_mint_failure() -> None:
 
     # First exec call = debit (succeeds), second = restore
     session = MagicMock()
+    session.get = AsyncMock(return_value=key)
     session.exec = AsyncMock(side_effect=[_update_result(1), _update_result(1)])
     session.commit = AsyncMock()
 
     with (
-        patch("routstr.balance.validate_bearer_key", AsyncMock(return_value=key)),
         patch("routstr.balance.get_billing_key", AsyncMock(return_value=key)),
         patch("routstr.balance.send_token", AsyncMock(side_effect=Exception("mint down"))),
         patch("routstr.balance.store_cashu_transaction", AsyncMock()),
@@ -355,3 +355,49 @@ async def test_apikey_refund_restores_balance_on_mint_failure() -> None:
     assert exc_info.value.status_code == 503
     # Verify two exec calls: debit + restore
     assert session.exec.await_count == 2
+
+
+# ---------------------------------------------------------------------------
+# no-create guarantee: fresh Cashu/unknown sk- tokens must not create API keys
+# ---------------------------------------------------------------------------
+
+
+@pytest.mark.asyncio
+async def test_refund_fresh_cashu_bearer_returns_401() -> None:
+    """Fresh Cashu token not in DB must get 401, never create a new ApiKey."""
+    from fastapi import HTTPException
+
+    session = MagicMock()
+    session.get = AsyncMock(return_value=None)
+
+    with pytest.raises(HTTPException) as exc_info:
+        await refund_wallet_endpoint(
+            authorization="Bearer cashuAfresh_never_deposited_token",
+            x_cashu=None,
+            session=session,
+        )
+
+    assert exc_info.value.status_code == 401
+    session.get.assert_awaited_once()
+    # No add/commit → no key was persisted
+    session.add.assert_not_called()
+    session.commit.assert_not_called()
+
+
+@pytest.mark.asyncio
+async def test_refund_unknown_sk_bearer_returns_401() -> None:
+    """Unknown sk- key not in DB must get 401."""
+    from fastapi import HTTPException
+
+    session = MagicMock()
+    session.get = AsyncMock(return_value=None)
+
+    with pytest.raises(HTTPException) as exc_info:
+        await refund_wallet_endpoint(
+            authorization="Bearer sk-unknownhash",
+            x_cashu=None,
+            session=session,
+        )
+
+    assert exc_info.value.status_code == 401
+    session.get.assert_awaited_once()

tests/unit/test_cost_calculation_caching.py

@@ -0,0 +1,345 @@
+"""Tests for cache token handling in cost calculation.
+
+Covers OpenAI vs Anthropic caching formats, edge cases, and billing accuracy.
+"""
+
+import os
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+os.environ.setdefault("UPSTREAM_BASE_URL", "http://test")
+os.environ.setdefault("UPSTREAM_API_KEY", "test")
+os.environ.setdefault("LIGHTNING_ADDRESS", "test@stm.to")
+
+from routstr.core.settings import settings
+from routstr.payment.cost_calculation import CostData, MaxCostData, calculate_cost
+
+
+@pytest.fixture
+def mock_session() -> AsyncMock:
+    """Mock AsyncSession for cost calculation tests."""
+    return AsyncMock()
+
+
+@pytest.fixture(autouse=True)
+def mock_fixed_pricing(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Mock settings and price to use fixed pricing."""
+    monkeypatch.setattr(settings, "fixed_pricing", True)
+    monkeypatch.setattr(settings, "fixed_per_1k_input_tokens", 0.001)
+    monkeypatch.setattr(settings, "fixed_per_1k_output_tokens", 0.001)
+
+
+@pytest.fixture(autouse=True)
+def patch_sats_usd_price() -> None:  # type: ignore[misc]
+    """Patch sats_usd_price to avoid initialization issues."""
+    with patch("routstr.payment.cost_calculation.sats_usd_price", return_value=5.0e-5):
+        yield
+
+
+# ============================================================================
+# Test 1: OpenAI Cache Format
+# ============================================================================
+@pytest.mark.asyncio
+async def test_openai_cache_subtraction(mock_session: AsyncMock) -> None:
+    """OpenAI includes cached_tokens in prompt_tokens, subtract them."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 2000,  # ← Includes 1000 cached
+            "completion_tokens": 100,
+            "prompt_tokens_details": {
+                "cached_tokens": 1000  # ← Extracted separately
+            }
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 1000  # 2000 - 1000
+    assert result.cache_read_input_tokens == 1000
+    assert result.output_tokens == 100
+
+
+# ============================================================================
+# Test 2: Anthropic Cache Format
+# ============================================================================
+@pytest.mark.asyncio
+async def test_anthropic_cache_additive(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Anthropic cache tokens are separate (additive) from input_tokens."""
+    response = {
+        "model": "claude-3-5-sonnet",
+        "usage": {
+            "input_tokens": 500,  # ← Regular input only
+            "output_tokens": 100,
+            "cache_creation_input_tokens": 1500,  # ← Additive, not included above
+            "cache_read_input_tokens": 0,
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 500
+    assert result.cache_creation_input_tokens == 1500
+    assert result.cache_read_input_tokens == 0
+    assert result.output_tokens == 100
+
+
+# ============================================================================
+# Test 3: Invalid Cache (Edge Case)
+# ============================================================================
+@pytest.mark.asyncio
+async def test_cache_read_exceeds_prompt_tokens(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle buggy upstream reporting cached > prompt_tokens."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 100,
+            "completion_tokens": 50,
+            "prompt_tokens_details": {
+                "cached_tokens": 150  # ← Invalid! Greater than prompt
+            }
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    # Should not go negative
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 0  # max(0, 100 - 150)
+    assert result.cache_read_input_tokens == 150
+    assert result.output_tokens == 50
+
+
+# ============================================================================
+# Test 4: Malformed Token Values
+# ============================================================================
+@pytest.mark.asyncio
+async def test_malformed_cache_tokens_coerce_to_zero(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle non-numeric cache token values."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 100,
+            "completion_tokens": 50,
+            "cache_read_input_tokens": "-50",  # ← String, negative
+            "prompt_tokens_details": {
+                "cached_tokens": "invalid"  # ← Non-numeric string
+            }
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    # Both should coerce to 0
+    assert isinstance(result, CostData)
+    assert result.cache_read_input_tokens == 0
+    assert result.input_tokens == 100  # No subtraction if cache_read = 0
+
+
+# ============================================================================
+# Test 5: Anthropic Cache Not Subtracted
+# ============================================================================
+@pytest.mark.asyncio
+async def test_anthropic_cache_not_subtracted(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Anthropic cache fields should NOT be subtracted from input_tokens."""
+    response = {
+        "model": "claude-3-5-sonnet",
+        "usage": {
+            "input_tokens": 500,
+            "completion_tokens": 100,
+            "cache_read_input_tokens": 200,  # ← Additive, don't subtract
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    # Anthropic: input_tokens stays as-is
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 500  # NOT 300
+    assert result.cache_read_input_tokens == 200
+
+
+# ============================================================================
+# Test 6: Only Cache Read, No Regular Input
+# ============================================================================
+@pytest.mark.asyncio
+async def test_only_cache_read_tokens(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle response with only cache read tokens."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 0,
+            "completion_tokens": 50,
+            "prompt_tokens_details": {
+                "cached_tokens": 1000
+            }
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 0  # max(0, 0 - 1000)
+    assert result.cache_read_input_tokens == 1000
+    assert result.output_tokens == 50
+
+
+# ============================================================================
+# Test 7: Only Cache Creation
+# ============================================================================
+@pytest.mark.asyncio
+async def test_only_cache_creation_tokens(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle response with only cache creation tokens (Anthropic)."""
+    response = {
+        "model": "claude-3-5-sonnet",
+        "usage": {
+            "input_tokens": 500,
+            "output_tokens": 100,
+            "cache_creation_input_tokens": 2000,
+            "cache_read_input_tokens": 0,
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 500
+    assert result.cache_creation_input_tokens == 2000
+    assert result.cache_read_input_tokens == 0
+    assert result.output_tokens == 100
+
+
+# ============================================================================
+# Test 8: Both Cache Read and Creation
+# ============================================================================
+@pytest.mark.asyncio
+async def test_both_cache_read_and_creation(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle response with both cache read and creation."""
+    response = {
+        "model": "claude-3-5-sonnet",
+        "usage": {
+            "input_tokens": 300,
+            "output_tokens": 100,
+            "cache_creation_input_tokens": 2000,
+            "cache_read_input_tokens": 500,
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 300
+    assert result.cache_creation_input_tokens == 2000
+    assert result.cache_read_input_tokens == 500
+    assert result.output_tokens == 100
+
+
+# ============================================================================
+# Test 9: Token Field Fallback
+# ============================================================================
+@pytest.mark.asyncio
+async def test_token_field_fallback_order(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Verify fallback order for token extraction."""
+    # When prompt_tokens is not present, fall back to input_tokens
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "input_tokens": 250,
+            "completion_tokens": 50,
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 250
+    assert result.output_tokens == 50
+
+
+# ============================================================================
+# Test 10: Float Token Values
+# ============================================================================
+@pytest.mark.asyncio
+async def test_float_token_values_coerced_to_int(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle float token values by converting to int."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 100.7,  # Float
+            "completion_tokens": 50.3,  # Float
+            "cache_read_input_tokens": 25.9,  # Float
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.input_tokens == 100  # Floored
+    assert result.output_tokens == 50  # Floored
+    assert result.cache_read_input_tokens == 25  # Floored
+
+
+# ============================================================================
+# Test 11: Boolean Cache Tokens
+# ============================================================================
+@pytest.mark.asyncio
+async def test_boolean_cache_tokens_coerced_to_zero(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle boolean cache token values by coercing to zero."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 100,
+            "completion_tokens": 50,
+            "cache_read_input_tokens": True,  # Boolean
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.cache_read_input_tokens == 0  # Boolean coerced to 0
+    assert result.input_tokens == 100  # No subtraction
+
+
+# ============================================================================
+# Test 12: Zero Cache Tokens
+# ============================================================================
+@pytest.mark.asyncio
+async def test_zero_cache_tokens(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """Handle explicit zero cache tokens."""
+    response = {
+        "model": "gpt-4",
+        "usage": {
+            "prompt_tokens": 100,
+            "completion_tokens": 50,
+            "prompt_tokens_details": {
+                "cached_tokens": 0
+            }
+        }
+    }
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, CostData)
+    assert result.cache_read_input_tokens == 0
+    assert result.input_tokens == 100
+
+
+# ============================================================================
+# Test 13: Missing Usage Block
+# ============================================================================
+@pytest.mark.asyncio
+async def test_missing_usage_block(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """When usage is missing, return MaxCostData with zero tokens."""
+    response = {"model": "gpt-4", "choices": [{"message": {"content": "test"}}]}
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, MaxCostData)
+    assert result.input_tokens == 0
+    assert result.cache_read_input_tokens == 0
+    assert result.output_tokens == 0
+
+
+# ============================================================================
+# Test 14: Null Usage Block
+# ============================================================================
+@pytest.mark.asyncio
+async def test_null_usage_block(mock_session: AsyncMock, mock_fixed_pricing: None) -> None:
+    """When usage is null, return MaxCostData with zero tokens."""
+    response = {"model": "gpt-4", "usage": None}
+    result = await calculate_cost(response, max_cost=100000, session=mock_session)
+
+    assert isinstance(result, MaxCostData)
+    assert result.input_tokens == 0
+    assert result.cache_read_input_tokens == 0

tests/unit/test_count_tokens_local.py

@@ -0,0 +1,177 @@
+"""Unit tests for the local count_tokens shim.
+
+The shim runs whenever an upstream that does not support Anthropic's
+``/v1/messages`` endpoint is asked for a token count. It must always
+return a 200 JSON ``{"input_tokens": N}`` response and must never raise.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+from unittest.mock import patch
+
+from routstr.payment.models import Architecture, Model, Pricing
+from routstr.upstream import count_tokens as count_tokens_module
+from routstr.upstream.count_tokens import count_tokens_locally
+
+
+def _make_model(model_id: str = "anthropic/claude-3-5-sonnet") -> Model:
+    pricing = Pricing(prompt=0.000003, completion=0.000015)
+    architecture = Architecture(
+        modality="text",
+        input_modalities=["text"],
+        output_modalities=["text"],
+        tokenizer="cl100k_base",
+        instruct_type=None,
+    )
+    return Model(
+        id=model_id,
+        name=model_id,
+        created=0,
+        description="",
+        context_length=200_000,
+        architecture=architecture,
+        pricing=pricing,
+    )
+
+
+def _body(payload: dict[str, Any]) -> bytes:
+    return json.dumps(payload).encode()
+
+
+def _read_payload(response: Any) -> dict[str, Any]:
+    body = response.body if isinstance(response.body, bytes) else bytes(response.body)
+    return json.loads(body.decode())
+
+
+def test_returns_input_tokens_for_simple_messages() -> None:
+    model = _make_model()
+    request_body = _body(
+        {
+            "model": model.id,
+            "messages": [{"role": "user", "content": "hello world"}],
+        }
+    )
+
+    response = count_tokens_locally(request_body, model)
+
+    assert response.status_code == 200
+    assert response.media_type == "application/json"
+    payload = _read_payload(response)
+    assert "input_tokens" in payload
+    assert isinstance(payload["input_tokens"], int)
+    assert payload["input_tokens"] >= 0
+
+
+def test_falls_back_to_estimator_when_litellm_raises() -> None:
+    model = _make_model()
+    request_body = _body(
+        {
+            "model": model.id,
+            "messages": [{"role": "user", "content": "this is a longer message"}],
+        }
+    )
+
+    with patch.object(
+        count_tokens_module,
+        "_count_with_litellm",
+        side_effect=RuntimeError("boom"),
+    ):
+        response = count_tokens_locally(request_body, model)
+
+    assert response.status_code == 200
+    payload = _read_payload(response)
+    assert payload["input_tokens"] >= 1
+
+
+def test_handles_missing_model_object() -> None:
+    request_body = _body(
+        {
+            "model": "anthropic/claude-3-5-sonnet",
+            "messages": [{"role": "user", "content": "hi"}],
+        }
+    )
+
+    response = count_tokens_locally(request_body, None)
+
+    assert response.status_code == 200
+    payload = _read_payload(response)
+    assert payload["input_tokens"] >= 0
+
+
+def test_handles_empty_request_body() -> None:
+    response = count_tokens_locally(b"", _make_model())
+
+    assert response.status_code == 200
+    payload = _read_payload(response)
+    assert payload["input_tokens"] >= 0
+
+
+def test_handles_malformed_json() -> None:
+    response = count_tokens_locally(b"not-json", _make_model())
+
+    assert response.status_code == 200
+    payload = _read_payload(response)
+    assert payload["input_tokens"] >= 0
+
+
+def test_includes_system_prompt_in_count() -> None:
+    model = _make_model()
+    short = _body(
+        {
+            "model": model.id,
+            "messages": [{"role": "user", "content": "hi"}],
+        }
+    )
+    with_system = _body(
+        {
+            "model": model.id,
+            "system": "You are a helpful assistant with a long preamble " * 10,
+            "messages": [{"role": "user", "content": "hi"}],
+        }
+    )
+
+    short_count = _read_payload(count_tokens_locally(short, model))["input_tokens"]
+    long_count = _read_payload(count_tokens_locally(with_system, model))["input_tokens"]
+
+    assert long_count > short_count
+
+
+def test_supports_anthropic_system_block_list() -> None:
+    model = _make_model()
+    request_body = _body(
+        {
+            "model": model.id,
+            "system": [{"type": "text", "text": "be terse" * 50}],
+            "messages": [{"role": "user", "content": "ok"}],
+        }
+    )
+
+    response = count_tokens_locally(request_body, model)
+
+    payload = _read_payload(response)
+    assert payload["input_tokens"] > 0
+
+
+def test_uses_forwarded_model_id_when_present() -> None:
+    model = _make_model("anthropic/claude-3-5-sonnet")
+    model.forwarded_model_id = "claude-3-5-sonnet-20241022"
+    request_body = _body(
+        {
+            "model": "ignored",
+            "messages": [{"role": "user", "content": "hi"}],
+        }
+    )
+
+    captured: dict[str, Any] = {}
+
+    def _capture(model_name: str, body: dict[str, Any]) -> int:
+        captured["model"] = model_name
+        return 7
+
+    with patch.object(count_tokens_module, "_count_with_litellm", side_effect=_capture):
+        response = count_tokens_locally(request_body, model)
+
+    assert captured["model"] == "claude-3-5-sonnet-20241022"
+    assert _read_payload(response)["input_tokens"] == 7

tests/unit/test_messages_dispatch_cost_accumulation.py

@@ -0,0 +1,333 @@
+"""Tests for cost accumulation in streaming message dispatch.
+
+Verifies that costs are correctly summed across multiple streaming events,
+not taking only the maximum.
+"""
+
+import os
+
+import pytest
+
+os.environ.setdefault("UPSTREAM_BASE_URL", "http://test")
+os.environ.setdefault("UPSTREAM_API_KEY", "test")
+
+from routstr.upstream.messages_dispatch import annotate_event
+
+
+# ============================================================================
+# Test 1: Cost Accumulation via AnnotatedEvent
+# ============================================================================
+@pytest.mark.unit
+def test_annotate_event_extracts_costs() -> None:
+    """Each event should report its own costs."""
+    event = {
+        "type": "content_block_start",
+        "usage": {"total_cost": 0.010, "input_cost": 0.008, "output_cost": 0.002}
+    }
+    result = annotate_event(event, None)
+
+    assert result.total_cost == 0.010
+    assert result.input_cost == 0.008
+    assert result.output_cost == 0.002
+
+
+# ============================================================================
+# Test 2: Multiple Events with Incremental Costs
+# ============================================================================
+@pytest.mark.unit
+def test_multiple_events_sum_costs() -> None:
+    """When processing multiple events, costs should accumulate (not max)."""
+    # Event 1: initial costs
+    event1 = {
+        "type": "message_start",
+        "usage": {"input_tokens": 100, "total_cost": 0.010}
+    }
+    result1 = annotate_event(event1, None)
+
+    # Event 2: additional costs
+    event2 = {
+        "type": "content_block_start",
+        "usage": {"output_tokens": 50, "total_cost": 0.005}
+    }
+    result2 = annotate_event(event2, None)
+
+    # Event 3: more costs
+    event3 = {
+        "type": "message_delta",
+        "usage": {"output_tokens": 25, "total_cost": 0.008}
+    }
+    result3 = annotate_event(event3, None)
+
+    # Each event should report its own cost (before accumulation)
+    assert result1.total_cost == 0.010
+    assert result2.total_cost == 0.005
+    assert result3.total_cost == 0.008
+
+    # When summed for billing: 0.010 + 0.005 + 0.008 = 0.023
+    # This verifies the cost accumulation fix (using += instead of max())
+    total_from_events = result1.total_cost + result2.total_cost + result3.total_cost
+    assert total_from_events == 0.023
+
+
+# ============================================================================
+# Test 3: Token Accumulation Consistency
+# ============================================================================
+@pytest.mark.unit
+def test_tokens_and_costs_extracted_independently() -> None:
+    """Tokens and costs should be extracted independently per event."""
+    event = {
+        "type": "content_block_delta",
+        "usage": {
+            "input_tokens": 100,
+            "output_tokens": 50,
+            "cache_read_input_tokens": 30,
+            "total_cost": 0.007,
+            "input_cost": 0.005,
+            "output_cost": 0.002
+        }
+    }
+    result = annotate_event(event, None)
+
+    # All values should be extracted
+    assert result.input_tokens == 100
+    assert result.output_tokens == 50
+    assert result.cache_read_input_tokens == 30
+    assert result.total_cost == 0.007
+    assert result.input_cost == 0.005
+    assert result.output_cost == 0.002
+
+
+# ============================================================================
+# Test 4: Cost in Message vs Root
+# ============================================================================
+@pytest.mark.unit
+def test_cost_extracted_from_message_usage() -> None:
+    """Costs in message.usage should be extracted correctly."""
+    event = {
+        "type": "message_start",
+        "message": {
+            "usage": {
+                "input_tokens": 100,
+                "total_cost": 0.010,
+                "input_cost": 0.008,
+                "output_cost": 0.002
+            }
+        }
+    }
+    result = annotate_event(event, None)
+
+    assert result.input_tokens == 100
+    assert result.total_cost == 0.010
+    assert result.input_cost == 0.008
+    assert result.output_cost == 0.002
+
+
+# ============================================================================
+# Test 5: Cost at Event Root Level
+# ============================================================================
+@pytest.mark.unit
+def test_cost_extracted_from_event_root() -> None:
+    """Costs at event root should be extracted (OpenRouter style)."""
+    event = {
+        "type": "content_block_delta",
+        "usage": {"output_tokens": 25},
+        "total_cost": 0.005,  # ← At root level
+        "cost": 0.005
+    }
+    result = annotate_event(event, None)
+
+    assert result.output_tokens == 25
+    assert result.total_cost == 0.005
+
+
+# ============================================================================
+# Test 6: Cost Details in Event Root
+# ============================================================================
+@pytest.mark.unit
+def test_cost_details_extracted_from_event_root() -> None:
+    """cost_details at event root should be extracted correctly."""
+    event = {
+        "type": "message_delta",
+        "cost_details": {
+            "total_cost": 0.015,
+            "input_cost": 0.010,
+            "output_cost": 0.005
+        }
+    }
+    result = annotate_event(event, None)
+
+    assert result.total_cost == 0.015
+    assert result.input_cost == 0.010
+    assert result.output_cost == 0.005
+
+
+# ============================================================================
+# Test 7: No Duplicated Dict Lookups
+# ============================================================================
+@pytest.mark.unit
+def test_annotate_event_no_duplicate_lookups() -> None:
+    """Verify that dict lookups are not duplicated (fix for copy-paste error)."""
+    # This is tested implicitly through proper extraction
+    event = {
+        "type": "message_delta",
+        "cost_details": {
+            "total_cost": 0.020,
+            "input_cost": 0.015,
+            "output_cost": 0.005
+        }
+    }
+    result = annotate_event(event, None)
+
+    # Should extract each field exactly once, correctly
+    assert result.total_cost == 0.020
+    assert result.input_cost == 0.015
+    assert result.output_cost == 0.005
+
+
+# ============================================================================
+# Test 8: Model Name Extraction
+# ============================================================================
+@pytest.mark.unit
+def test_model_extracted_from_event() -> None:
+    """Model name should be extracted from event."""
+    event = {
+        "type": "message_start",
+        "message": {"model": "claude-3-5-sonnet"}
+    }
+    result = annotate_event(event, None)
+
+    assert result.model == "claude-3-5-sonnet"
+
+
+# ============================================================================
+# Test 9: Model Name Override
+# ============================================================================
+@pytest.mark.unit
+def test_model_name_override() -> None:
+    """Requested model should override actual model in event."""
+    event = {
+        "type": "message_start",
+        "message": {"model": "actual-model"}
+    }
+    # Override with requested_model
+    result = annotate_event(event, requested_model="alias-model")
+
+    # Event should be modified to use requested_model
+    assert event["message"]["model"] == "alias-model"  # type: ignore[index]
+    assert result.model == "alias-model"
+
+
+# ============================================================================
+# Test 10: SSE Encoding
+# ============================================================================
+@pytest.mark.unit
+def test_sse_bytes_encoded() -> None:
+    """Event should be encoded as SSE bytes."""
+    event = {
+        "type": "content_block_start",
+        "index": 0,
+        "content_block": {"type": "text", "text": ""}
+    }
+    result = annotate_event(event, None)
+
+    assert result.sse_bytes is not None
+    assert isinstance(result.sse_bytes, bytes)
+    assert b"event: content_block_start" in result.sse_bytes or b"data:" in result.sse_bytes
+
+
+# ============================================================================
+# Test 11: Missing Cost Fields Default to Zero
+# ============================================================================
+@pytest.mark.unit
+def test_missing_cost_fields_default_to_zero() -> None:
+    """When cost fields are missing, should default to 0.0."""
+    event = {
+        "type": "content_block_delta",
+        "usage": {"output_tokens": 25}
+        # No cost fields
+    }
+    result = annotate_event(event, None)
+
+    assert result.total_cost == 0.0
+    assert result.input_cost == 0.0
+    assert result.output_cost == 0.0
+
+
+# ============================================================================
+# Test 12: Cache Tokens in Events
+# ============================================================================
+@pytest.mark.unit
+def test_cache_tokens_extracted_from_event() -> None:
+    """Cache tokens should be extracted from event usage."""
+    event = {
+        "type": "message_delta",
+        "usage": {
+            "input_tokens": 100,
+            "output_tokens": 50,
+            "cache_read_input_tokens": 200,
+            "cache_creation_input_tokens": 0
+        }
+    }
+    result = annotate_event(event, None)
+
+    assert result.input_tokens == 100
+    assert result.output_tokens == 50
+    assert result.cache_read_input_tokens == 200
+    assert result.cache_creation_input_tokens == 0
+
+
+# ============================================================================
+# Test 13: Malformed Cost Values
+# ============================================================================
+@pytest.mark.unit
+def test_malformed_cost_values_coerced() -> None:
+    """Malformed cost values should be coerced to 0.0."""
+    event = {
+        "type": "message_delta",
+        "usage": {
+            "input_tokens": 100,
+            "output_tokens": 50,
+            "total_cost": "invalid",  # ← Non-numeric
+        }
+    }
+    result = annotate_event(event, None)
+
+    # Invalid cost should default to 0.0
+    assert result.total_cost == 0.0
+
+
+# ============================================================================
+# Test 14: Negative Cost Values
+# ============================================================================
+@pytest.mark.unit
+def test_negative_cost_values_clamped() -> None:
+    """Negative cost values should be clamped to 0.0."""
+    event = {
+        "type": "message_delta",
+        "usage": {
+            "input_tokens": 100,
+            "output_tokens": 50,
+            "total_cost": -0.05  # ← Negative
+        }
+    }
+    result = annotate_event(event, None)
+
+    # Negative cost should be clamped to 0.0
+    assert result.total_cost == 0.0
+
+
+# ============================================================================
+# Test 15: Streaming Event Type Preserved
+# ============================================================================
+@pytest.mark.unit
+def test_event_type_preserved_in_sse() -> None:
+    """Event type should be preserved in SSE encoding."""
+    event_types = ["message_start", "content_block_start", "content_block_delta", "message_delta"]
+    for event_type in event_types:
+        event = {"type": event_type}
+        result = annotate_event(event, None)
+
+        assert result.event["type"] == event_type  # type: ignore[index]
+        # SSE should include the event type line if present
+        if event_type:
+            assert f"event: {event_type}".encode() in result.sse_bytes

tests/unit/test_messages_litellm_dispatch.py

@@ -908,7 +908,7 @@ async def test_forward_request_skips_litellm_when_provider_supports_messages() -
 
 
 @pytest.mark.asyncio
-async def test_forward_request_skips_litellm_for_count_tokens() -> None:
+async def test_forward_request_handles_count_tokens_locally() -> None:
     provider = _make_provider()
     key = _make_key()
     model = _make_model()
@@ -923,19 +923,25 @@ async def test_forward_request_skips_litellm_for_count_tokens() -> None:
         with patch.object(
             provider,
             "prepare_request_body",
-            side_effect=RuntimeError("stop here"),
+            side_effect=AssertionError("upstream should not be called"),
         ):
-            with pytest.raises(RuntimeError, match="stop here"):
-                await provider.forward_request(
-                    request=request,
-                    path="messages/count_tokens",
-                    headers={},
-                    request_body=_anthropic_request_body(),
-                    key=key,
-                    max_cost_for_model=10_000,
-                    session=session,
-                    model_obj=model,
-                )
+            response = await provider.forward_request(
+                request=request,
+                path="messages/count_tokens",
+                headers={},
+                request_body=_anthropic_request_body(),
+                key=key,
+                max_cost_for_model=10_000,
+                session=session,
+                model_obj=model,
+            )
+
+    assert response.status_code == 200
+    body = response.body if isinstance(response.body, bytes) else bytes(response.body)
+    payload = json.loads(body.decode())
+    assert "input_tokens" in payload
+    assert isinstance(payload["input_tokens"], int)
+    assert payload["input_tokens"] >= 0
 
 
 # ---------------------------------------------------------------------------
@@ -1010,7 +1016,7 @@ async def test_forward_x_cashu_request_skips_litellm_when_native_messages() -> N
 
 
 @pytest.mark.asyncio
-async def test_forward_x_cashu_request_skips_litellm_for_count_tokens() -> None:
+async def test_forward_x_cashu_request_handles_count_tokens_locally() -> None:
     provider = _make_provider()
     model = _make_model()
     request = _make_request()
@@ -1024,18 +1030,24 @@ async def test_forward_x_cashu_request_skips_litellm_for_count_tokens() -> None:
         with patch.object(
             provider,
             "prepare_request_body",
-            side_effect=RuntimeError("stop here"),
+            side_effect=AssertionError("upstream should not be called"),
         ):
-            with pytest.raises(RuntimeError, match="stop here"):
-                await provider.forward_x_cashu_request(
-                    request=request,
-                    path="v1/messages/count_tokens",
-                    headers={},
-                    amount=5_000,
-                    unit="sat",
-                    max_cost_for_model=10_000,
-                    model_obj=model,
-                )
+            response = await provider.forward_x_cashu_request(
+                request=request,
+                path="v1/messages/count_tokens",
+                headers={},
+                amount=5_000,
+                unit="sat",
+                max_cost_for_model=10_000,
+                model_obj=model,
+                mint="https://mint",
+                payment_token_hash="h",
+            )
+
+    assert response.status_code == 200
+    body = response.body if isinstance(response.body, bytes) else bytes(response.body)
+    payload = json.loads(body.decode())
+    assert "input_tokens" in payload
 
 
 # ---------------------------------------------------------------------------

tests/unit/test_proxy_not_found.py

@@ -0,0 +1,70 @@
+"""Tests for the app-level 404 handler in routstr.core.main."""
+
+from __future__ import annotations
+
+import pytest
+from fastapi import FastAPI
+from fastapi.testclient import TestClient
+
+from routstr.core import main as core_main
+
+
+def _make_app() -> FastAPI:
+    app = FastAPI()
+    app.add_api_route(
+        "/{path:path}",
+        core_main.not_found_catch_all,
+        methods=["GET", "POST"],
+        include_in_schema=False,
+    )
+    return app
+
+
+@pytest.mark.skipif(
+    core_main._NOT_FOUND_HTML is None,
+    reason="UI bundle (ui_out/404.html) not present in this environment",
+)
+def test_unknown_path_returns_html_404_for_browser() -> None:
+    client = TestClient(_make_app())
+    response = client.get("/some/random/page", headers={"accept": "text/html"})
+    assert response.status_code == 404
+    assert response.headers["content-type"].startswith("text/html")
+    assert "404" in response.text
+
+
+def test_unknown_path_returns_json_404_for_api_client() -> None:
+    client = TestClient(_make_app())
+    response = client.get(
+        "/some/random/page", headers={"accept": "application/json"}
+    )
+    assert response.status_code == 404
+    assert response.headers["content-type"].startswith("application/json")
+    payload = response.json()
+    assert payload["error"]["type"] == "not_found"
+    assert payload["error"]["code"] == 404
+    assert "/some/random/page" in payload["error"]["message"]
+
+
+def test_root_path_returns_404() -> None:
+    client = TestClient(_make_app())
+    response = client.get("/", headers={"accept": "application/json"})
+    assert response.status_code == 404
+
+
+def test_json_returned_when_ui_html_missing(monkeypatch: pytest.MonkeyPatch) -> None:
+    from routstr.core import not_found as nf
+
+    monkeypatch.setattr(nf, "_NOT_FOUND_HTML", None)
+    client = TestClient(_make_app())
+    response = client.get("/some/random/page", headers={"accept": "text/html"})
+    assert response.status_code == 404
+    assert response.headers["content-type"].startswith("application/json")
+
+
+def test_post_unknown_path_returns_json_even_for_browser() -> None:
+    client = TestClient(_make_app())
+    response = client.post("/some/random/page", headers={"accept": "text/html"})
+    assert response.status_code == 404
+    assert response.headers["content-type"].startswith("application/json")
+    payload = response.json()
+    assert payload["error"]["type"] == "not_found"

tests/unit/test_settings.py

@@ -1,11 +1,12 @@
 import os
 
 import pytest
+from pydantic.v1 import ValidationError
 from sqlalchemy.ext.asyncio import create_async_engine
 from sqlmodel import text
 from sqlmodel.ext.asyncio.session import AsyncSession
 
-from routstr.core.settings import SettingsService
+from routstr.core.settings import Settings, SettingsService
 
 
 @pytest.mark.asyncio
@@ -46,6 +47,54 @@ async def test_settings_db_precedence_over_env() -> None:
         assert again.enable_analytics_sharing is False
 
 
+def test_payout_settings_have_sensible_defaults() -> None:
+    s = Settings()
+    assert s.min_payout_sat == 210
+    assert s.payout_interval_seconds == 900
+
+
+@pytest.mark.parametrize(
+    "field,bad_value",
+    [
+        ("min_payout_sat", 0),
+        ("min_payout_sat", -1),
+        ("payout_interval_seconds", 0),
+        ("payout_interval_seconds", -10),
+    ],
+)
+def test_payout_settings_reject_invalid_values(field: str, bad_value: int) -> None:
+    kwargs: dict[str, object] = {field: bad_value}
+    with pytest.raises(ValidationError):
+        Settings(**kwargs)  # type: ignore[arg-type]
+
+
+def test_payout_settings_accept_custom_positive_values() -> None:
+    s = Settings(min_payout_sat=500, payout_interval_seconds=60)
+    assert s.min_payout_sat == 500
+    assert s.payout_interval_seconds == 60
+
+
+@pytest.mark.asyncio
+async def test_payout_settings_persist_via_settings_service() -> None:
+    engine = create_async_engine("sqlite+aiosqlite:///:memory:")
+    async with AsyncSession(engine, expire_on_commit=False) as session:
+        await SettingsService.initialize(session)
+        updated = await SettingsService.update(
+            {"min_payout_sat": 1000, "payout_interval_seconds": 300}, session
+        )
+        assert updated.min_payout_sat == 1000
+        assert updated.payout_interval_seconds == 300
+
+
+@pytest.mark.asyncio
+async def test_payout_settings_update_rejects_invalid() -> None:
+    engine = create_async_engine("sqlite+aiosqlite:///:memory:")
+    async with AsyncSession(engine, expire_on_commit=False) as session:
+        await SettingsService.initialize(session)
+        with pytest.raises(ValidationError):
+            await SettingsService.update({"min_payout_sat": 0}, session)
+
+
 @pytest.mark.asyncio
 async def test_settings_initialize_discards_unknown_keys() -> None:
     engine = create_async_engine("sqlite+aiosqlite:///:memory:")

tests/unit/test_upstream_error_response.py

@@ -0,0 +1,150 @@
+"""Tests for ``BaseUpstreamProvider.forward_upstream_error_response``.
+
+Upstream services (e.g. an Express server that doesn't expose ``/messages``)
+sometimes return a non-JSON error body. The proxy must surface those errors
+in a consistent JSON envelope so clients don't have to parse HTML.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+from unittest.mock import Mock
+
+import httpx
+import pytest
+
+from routstr.upstream.base import BaseUpstreamProvider, _is_json_content_type
+
+
+def _make_request(request_id: str = "req-123") -> Mock:
+    request = Mock(spec=["method", "state"])
+    request.method = "POST"
+    request.state = Mock()
+    request.state.request_id = request_id
+    return request
+
+
+def _make_upstream_response(
+    *,
+    body: bytes,
+    status_code: int = 404,
+    content_type: str | None = "text/html",
+    extra_headers: dict[str, str] | None = None,
+) -> httpx.Response:
+    headers: dict[str, str] = {}
+    if content_type is not None:
+        headers["content-type"] = content_type
+    if extra_headers:
+        headers.update(extra_headers)
+    return httpx.Response(status_code=status_code, headers=headers, content=body)
+
+
+@pytest.fixture
+def provider() -> BaseUpstreamProvider:
+    return BaseUpstreamProvider(
+        base_url="https://privateprovider.xyz", api_key="k", provider_fee=1.0
+    )
+
+
+@pytest.mark.parametrize(
+    "content_type,expected",
+    [
+        ("application/json", True),
+        ("application/json; charset=utf-8", True),
+        ("text/json", True),
+        ("application/problem+json", True),
+        ("application/vnd.api+json", True),
+        ("text/html", False),
+        ("text/html; charset=utf-8", False),
+        ("text/plain", False),
+        ("", False),
+        (None, False),
+    ],
+)
+def test_is_json_content_type(content_type: str | None, expected: bool) -> None:
+    assert _is_json_content_type(content_type) is expected
+
+
+@pytest.mark.asyncio
+async def test_html_error_is_normalized_to_json_envelope(
+    provider: BaseUpstreamProvider,
+) -> None:
+    html_body = (
+        b"<!DOCTYPE html><html><head><title>Error</title></head>"
+        b"<body><pre>Cannot POST /messages</pre></body></html>"
+    )
+    upstream = _make_upstream_response(body=html_body, status_code=404)
+
+    response = await provider.forward_upstream_error_response(
+        _make_request(), "v1/messages", upstream
+    )
+
+    assert response.status_code == 404
+    assert response.media_type == "application/json"
+    payload: dict[str, Any] = json.loads(bytes(response.body))
+    assert payload["error"]["type"] == "upstream_error"
+    assert payload["error"]["upstream_status"] == 404
+    assert payload["error"]["upstream_content_type"] == "text/html"
+    assert "Cannot POST /messages" in payload["error"]["upstream_body_preview"]
+    assert payload["request_id"] == "req-123"
+    # The upstream's text/html content-type must not survive — Response()
+    # sets the JSON content-type for us via media_type.
+    assert response.headers["content-type"].startswith("application/json")
+
+
+@pytest.mark.asyncio
+async def test_plain_text_error_is_normalized(
+    provider: BaseUpstreamProvider,
+) -> None:
+    upstream = _make_upstream_response(
+        body=b"Service Unavailable", status_code=503, content_type="text/plain"
+    )
+
+    response = await provider.forward_upstream_error_response(
+        _make_request(), "v1/messages", upstream
+    )
+
+    assert response.status_code == 503
+    assert response.media_type == "application/json"
+    payload = json.loads(bytes(response.body))
+    assert payload["error"]["message"] == "Service Unavailable"
+
+
+@pytest.mark.asyncio
+async def test_empty_body_with_non_json_content_type_normalizes(
+    provider: BaseUpstreamProvider,
+) -> None:
+    upstream = _make_upstream_response(
+        body=b"", status_code=502, content_type="text/html"
+    )
+
+    response = await provider.forward_upstream_error_response(
+        _make_request(), "v1/messages", upstream
+    )
+
+    assert response.status_code == 502
+    assert response.media_type == "application/json"
+    payload = json.loads(bytes(response.body))
+    assert payload["error"]["type"] == "upstream_error"
+    assert payload["error"]["upstream_body_preview"] is None
+
+
+@pytest.mark.asyncio
+async def test_json_error_body_is_passed_through_unchanged(
+    provider: BaseUpstreamProvider,
+) -> None:
+    json_body = json.dumps(
+        {"error": {"message": "Invalid model", "type": "invalid_request_error"}}
+    ).encode()
+    upstream = _make_upstream_response(
+        body=json_body, status_code=400, content_type="application/json"
+    )
+
+    response = await provider.forward_upstream_error_response(
+        _make_request(), "v1/messages", upstream
+    )
+
+    assert response.status_code == 400
+    assert bytes(response.body) == json_body
+    assert response.media_type == "application/json"

tests/unit/test_upstream_routstr.py

@@ -74,3 +74,39 @@ async def test_get_balance_returns_none_on_connect_timeout(
     balance = await provider.get_balance()
 
     assert balance is None
+
+
+def test_normalize_request_path_keeps_v1_prefix() -> None:
+    """Routstr upstream stores ``base_url`` without ``/v1``; the prefix
+    must stay on the path so ``build_request_url`` produces ``/v1/<endpoint>``
+    instead of ``/<endpoint>`` (which the upstream Routstr 404s with HTML)."""
+    provider = RoutstrUpstreamProvider(
+        base_url="https://privateprovider.xyz", api_key="key"
+    )
+
+    assert provider.normalize_request_path("v1/messages") == "v1/messages"
+    assert provider.normalize_request_path("/v1/messages") == "v1/messages"
+    assert (
+        provider.normalize_request_path("v1/chat/completions")
+        == "v1/chat/completions"
+    )
+
+
+def test_build_request_url_for_v1_messages() -> None:
+    """Forwarding ``/v1/messages`` must hit the upstream's ``/v1/messages``."""
+    provider = RoutstrUpstreamProvider(
+        base_url="https://privateprovider.xyz", api_key="key"
+    )
+
+    normalized = provider.normalize_request_path("v1/messages")
+
+    assert (
+        provider.build_request_url(normalized)
+        == "https://privateprovider.xyz/v1/messages"
+    )
+
+
+def test_supports_anthropic_messages_natively() -> None:
+    """Routstr nodes serve ``/v1/messages`` directly, so the proxy must
+    forward as-is instead of round-tripping through litellm."""
+    assert RoutstrUpstreamProvider.supports_anthropic_messages is True

tests/unit/test_wallet.py

@@ -123,6 +123,7 @@ async def test_swap_to_primary_mint_insufficient_for_fees() -> None:
     mock_token_wallet = Mock()
     mock_token_wallet.load_mint = AsyncMock()
     mock_token_wallet.load_proofs = AsyncMock()
+    mock_token_wallet.get_fees_for_proofs = Mock(return_value=0)
 
     mock_primary_wallet = Mock()
     mock_primary_wallet.load_mint = AsyncMock()
@@ -166,6 +167,7 @@ async def test_swap_to_primary_mint_melt_error_wrapped() -> None:
     mock_token_wallet = Mock()
     mock_token_wallet.load_mint = AsyncMock()
     mock_token_wallet.load_proofs = AsyncMock()
+    mock_token_wallet.get_fees_for_proofs = Mock(return_value=0)
 
     mock_primary_wallet = Mock()
     mock_primary_wallet.load_mint = AsyncMock()
@@ -261,6 +263,7 @@ async def test_swap_to_primary_mint_success() -> None:
     mock_token_wallet = Mock()
     mock_token_wallet.load_mint = AsyncMock()
     mock_token_wallet.load_proofs = AsyncMock()
+    mock_token_wallet.get_fees_for_proofs = Mock(return_value=0)
 
     mock_primary_wallet = Mock()
     mock_primary_wallet.load_mint = AsyncMock()

ui/components/add-provider-model-dialog.tsx

@@ -1,6 +1,6 @@
 'use client';
 
-import React, { useCallback, useEffect, useMemo, useState } from 'react';
+import React, { useEffect, useMemo, useState } from 'react';
 import { useForm } from 'react-hook-form';
 import { z } from 'zod';
 import { zodResolver } from '@hookform/resolvers/zod';

ui/components/app-page-shell.tsx

@@ -21,6 +21,7 @@ import { adminLogout } from '@/lib/api/services/auth';
 import { Button } from '@/components/ui/button';
 import { CurrencyToggle } from '@/components/currency-toggle';
 import { ThemeToggle } from '@/components/theme-toggle';
+import { VersionStatus } from '@/components/version-status';
 import {
   Sheet,
   SheetClose,
@@ -110,6 +111,7 @@ export function AppPageShell({
                   <h1 className='truncate text-lg font-semibold tracking-tight whitespace-nowrap'>
                     Routstr Node
                   </h1>
+                  <VersionStatus className='mt-0.5' />
                 </div>
               </div>
               <Button
@@ -279,9 +281,12 @@ export function AppPageShell({
                     height={24}
                     className='rounded-sm'
                   />
-                  <p className='truncate text-base font-medium tracking-tight'>
-                    Routstr Node
-                  </p>
+                  <div className='min-w-0'>
+                    <p className='truncate text-base font-medium tracking-tight'>
+                      Routstr Node
+                    </p>
+                    <VersionStatus className='mt-0.5' />
+                  </div>
                 </div>
                 <SheetClose asChild>
                   <Button

ui/components/settings/admin-settings.tsx

@@ -32,9 +32,18 @@ interface SettingsData {
   onion_url?: string;
   cashu_mints?: string[];
   relays?: string[];
+  receive_ln_address?: string;
+  min_payout_sat?: number;
+  payout_interval_seconds?: number;
   [key: string]: unknown;
 }
 
+const PAYOUT_KEYS = [
+  'receive_ln_address',
+  'min_payout_sat',
+  'payout_interval_seconds',
+] as const;
+
 const HANDLED_KEYS = [
   'name',
   'description',
@@ -48,6 +57,7 @@ const HANDLED_KEYS = [
   'admin_password',
   'id',
   'updated_at',
+  ...PAYOUT_KEYS,
 ];
 
 const IGNORED_KEYS = [
@@ -369,6 +379,7 @@ export function AdminSettings() {
   const cashuMintsChanged = hasFieldChanged('cashu_mints');
   const relaysChanged = hasFieldChanged('relays');
   const analyticsSharingChanged = hasFieldChanged('enable_analytics_sharing');
+  const payoutChanged = PAYOUT_KEYS.some(hasFieldChanged);
   const advancedKeys = Object.keys(settings).filter(
     (key) => !HANDLED_KEYS.includes(key) && !IGNORED_KEYS.includes(key)
   );
@@ -401,8 +412,44 @@ export function AdminSettings() {
     setNewRelay('');
   };
   const resetAnalyticsSharing = () => resetFields(['enable_analytics_sharing']);
+  const resetPayout = () => resetFields([...PAYOUT_KEYS]);
   const resetAdvanced = () => resetFields(advancedKeys);
 
+  const payoutFields: ReadonlyArray<{
+    key: (typeof PAYOUT_KEYS)[number];
+    label: string;
+    placeholder: string;
+    type: 'text' | 'number';
+    helpText: string;
+    min?: number;
+  }> = [
+    {
+      key: 'receive_ln_address',
+      label: 'Lightning Receive Address',
+      placeholder: 'you@walletofsatoshi.com or LNURL',
+      type: 'text',
+      helpText:
+        'Lightning address (or LNURL) profits are paid out to. Leave empty to disable periodic payouts.',
+    },
+    {
+      key: 'min_payout_sat',
+      label: 'Minimum Payout (sat)',
+      placeholder: '210',
+      type: 'number',
+      min: 1,
+      helpText:
+        'Wallet payouts only fire when at least this many satoshis are available. Must be > 0.',
+    },
+    {
+      key: 'payout_interval_seconds',
+      label: 'Payout Interval (seconds)',
+      placeholder: '900',
+      type: 'number',
+      min: 1,
+      helpText: 'How often the payout loop wakes up to check balances.',
+    },
+  ];
+
   if (loading) {
     return (
       <div className='space-y-4'>
@@ -620,6 +667,89 @@ export function AdminSettings() {
           ) : null}
         </Card>
 
+        {/* Lightning Payout Settings */}
+        <Card>
+          <CardHeader>
+            <CardTitle>Lightning Payout Settings</CardTitle>
+            <CardDescription>
+              Tune how node profit is paid out over Lightning. Amounts must be
+              positive and above your wallet&apos;s minimum-invoice constraints.
+            </CardDescription>
+          </CardHeader>
+          <CardContent className='space-y-4'>
+            {payoutFields.map((field) => {
+              const value = settings[field.key];
+              if (field.type === 'number') {
+                return (
+                  <div key={field.key} className='space-y-2'>
+                    <Label htmlFor={field.key}>{field.label}</Label>
+                    <Input
+                      id={field.key}
+                      type='number'
+                      min={field.min}
+                      value={
+                        typeof value === 'number'
+                          ? value
+                          : value === undefined || value === null
+                            ? ''
+                            : Number(value)
+                      }
+                      placeholder={field.placeholder}
+                      onChange={(e) => {
+                        const raw = e.target.value;
+                        if (raw === '') {
+                          handleInputChange(field.key, undefined);
+                        } else {
+                          const parsed = Number(raw);
+                          handleInputChange(
+                            field.key,
+                            Number.isFinite(parsed) ? parsed : undefined
+                          );
+                        }
+                      }}
+                    />
+                    <p className='text-muted-foreground text-xs'>
+                      {field.helpText}
+                    </p>
+                  </div>
+                );
+              }
+              return (
+                <div key={field.key} className='space-y-2'>
+                  <Label htmlFor={field.key}>{field.label}</Label>
+                  <Input
+                    id={field.key}
+                    value={(value as string) || ''}
+                    placeholder={field.placeholder}
+                    onChange={(e) =>
+                      handleInputChange(field.key, e.target.value)
+                    }
+                  />
+                  <p className='text-muted-foreground text-xs'>
+                    {field.helpText}
+                  </p>
+                </div>
+              );
+            })}
+          </CardContent>
+          {payoutChanged ? (
+            <CardFooter className='justify-start'>
+              <div className='flex w-full flex-col gap-2 sm:w-auto sm:flex-row sm:items-center'>
+                <Button
+                  variant='outline'
+                  onClick={resetPayout}
+                  disabled={loading || saving}
+                >
+                  Cancel
+                </Button>
+                <Button onClick={handleSave} disabled={loading || saving}>
+                  {saving ? 'Saving...' : 'Save'}
+                </Button>
+              </div>
+            </CardFooter>
+          ) : null}
+        </Card>
+
         {/* Relays */}
         <Card>
           <CardHeader>

ui/components/version-status.tsx

@@ -0,0 +1,282 @@
+'use client';
+
+import { useQuery, useQueryClient } from '@tanstack/react-query';
+import {
+  AlertTriangleIcon,
+  CheckCircle2Icon,
+  ExternalLinkIcon,
+  InfoIcon,
+  Loader2Icon,
+  RefreshCwIcon,
+} from 'lucide-react';
+import { ConfigurationService } from '@/lib/api/services/configuration';
+import { Button } from '@/components/ui/button';
+import {
+  Popover,
+  PopoverContent,
+  PopoverTrigger,
+} from '@/components/ui/popover';
+import { cn } from '@/lib/utils';
+import {
+  deriveStatus,
+  formatReleaseDate,
+  formatVersionLabel,
+  parseVersion,
+  type StatusKind,
+} from '@/lib/utils/version';
+
+interface NodeInfo {
+  version?: string;
+}
+
+interface GithubRelease {
+  tag_name: string;
+  name?: string;
+  html_url: string;
+  published_at?: string;
+  body?: string;
+}
+
+const NODE_QUERY_KEY = ['node-version'] as const;
+const RELEASE_QUERY_KEY = ['routstr-latest-release'] as const;
+const THIRTY_MINUTES = 30 * 60 * 1000;
+
+const GITHUB_RELEASES_URL = `https://api.github.com/repos/Routstr/routstr-core/releases/latest`;
+const RELEASES_PAGE_URL = `https://github.com/Routstr/routstr-core/releases`;
+
+async function fetchNodeInfo(): Promise<NodeInfo> {
+  const baseUrl = ConfigurationService.getLocalBaseUrl().replace(/\/+$/, '');
+  const response = await fetch(`${baseUrl}/v1/info`, {
+    headers: { 'Content-Type': 'application/json' },
+  });
+  if (!response.ok) {
+    throw new Error('Unable to load node info');
+  }
+  return (await response.json()) as NodeInfo;
+}
+
+async function fetchLatestRelease(): Promise<GithubRelease | null> {
+  const response = await fetch(GITHUB_RELEASES_URL, {
+    headers: { Accept: 'application/vnd.github+json' },
+  });
+  if (response.status === 403 || response.status === 404) {
+    return null;
+  }
+  if (!response.ok) {
+    throw new Error(`GitHub responded ${response.status}`);
+  }
+  return (await response.json()) as GithubRelease;
+}
+
+function pickColorClass(status: StatusKind): string {
+  if (status === 'outdated') return 'text-amber-600 dark:text-amber-400';
+  if (status === 'unknown') return 'text-muted-foreground';
+  if (status === 'ahead' || status === 'commit-drift') {
+    return 'text-sky-600 dark:text-sky-400';
+  }
+  return 'text-emerald-600 dark:text-emerald-400';
+}
+
+function renderStatusIcon(status: StatusKind, className: string) {
+  if (status === 'outdated') {
+    return <AlertTriangleIcon className={className} />;
+  }
+  if (status === 'commit-drift' || status === 'ahead' || status === 'unknown') {
+    return <InfoIcon className={className} />;
+  }
+  return <CheckCircle2Icon className={className} />;
+}
+
+function describeStatus(status: StatusKind): string {
+  if (status === 'outdated') return 'A newer release is available.';
+  if (status === 'commit-drift') {
+    return 'Running release version on a non-release commit.';
+  }
+  if (status === 'ahead') {
+    return 'Running ahead of the latest published release.';
+  }
+  if (status === 'current') return 'Up to date with the latest release.';
+  return 'Version status unavailable.';
+}
+
+interface VersionStatusProps {
+  variant?: 'expanded' | 'compact';
+  className?: string;
+}
+
+export function VersionStatus({
+  variant = 'expanded',
+  className,
+}: VersionStatusProps) {
+  const queryClient = useQueryClient();
+
+  const nodeQuery = useQuery({
+    queryKey: NODE_QUERY_KEY,
+    queryFn: fetchNodeInfo,
+    staleTime: THIRTY_MINUTES,
+    retry: 1,
+  });
+
+  const releaseQuery = useQuery({
+    queryKey: RELEASE_QUERY_KEY,
+    queryFn: fetchLatestRelease,
+    staleTime: THIRTY_MINUTES,
+    refetchInterval: THIRTY_MINUTES,
+    refetchOnWindowFocus: false,
+    retry: 1,
+  });
+
+  const currentVersion = parseVersion(nodeQuery.data?.version);
+  const latestVersion = parseVersion(releaseQuery.data?.tag_name);
+  const status = deriveStatus(currentVersion, latestVersion);
+
+  const isRefreshing = releaseQuery.isFetching || nodeQuery.isFetching;
+
+  const handleRefresh = async (): Promise<void> => {
+    await Promise.all([
+      queryClient.invalidateQueries({ queryKey: NODE_QUERY_KEY }),
+      queryClient.invalidateQueries({ queryKey: RELEASE_QUERY_KEY }),
+    ]);
+  };
+
+  const colorClass = pickColorClass(status);
+  const versionLabel = currentVersion
+    ? formatVersionLabel(currentVersion)
+    : nodeQuery.isLoading
+      ? '…'
+      : 'unknown';
+
+  if (!nodeQuery.data && nodeQuery.isLoading && variant === 'expanded') {
+    return null;
+  }
+
+  const statusDescription = describeStatus(status);
+  const ariaLabel = `Node version ${versionLabel}. ${statusDescription} Click for details.`;
+
+  const releaseRateLimited = releaseQuery.data === null;
+
+  return (
+    <Popover>
+      <PopoverTrigger asChild>
+        <button
+          type='button'
+          onClick={(e) => e.stopPropagation()}
+          className={cn(
+            'hover:bg-accent/40 inline-flex items-center gap-1 rounded-md px-1 py-0.5 font-mono text-[10px] leading-tight transition-colors',
+            colorClass,
+            className
+          )}
+          title='View version details'
+          aria-label={ariaLabel}
+        >
+          {renderStatusIcon(status, 'h-3 w-3 shrink-0')}
+          <span className='truncate'>{versionLabel}</span>
+        </button>
+      </PopoverTrigger>
+      <PopoverContent
+        side='bottom'
+        align='start'
+        sideOffset={6}
+        className='w-72 p-3'
+      >
+        <div className='flex items-start justify-between gap-2'>
+          <div className='min-w-0 space-y-0.5'>
+            <div className='flex items-center gap-1.5 text-sm font-medium'>
+              {renderStatusIcon(status, cn('h-4 w-4 shrink-0', colorClass))}
+              Node Version
+            </div>
+            <p className='text-muted-foreground text-xs leading-snug'>
+              {statusDescription}
+            </p>
+          </div>
+          <Button
+            type='button'
+            variant='outline'
+            size='icon'
+            className='h-7 w-7 shrink-0'
+            onClick={handleRefresh}
+            disabled={isRefreshing}
+            title='Check for latest release'
+          >
+            {isRefreshing ? (
+              <Loader2Icon className='h-3.5 w-3.5 animate-spin' />
+            ) : (
+              <RefreshCwIcon className='h-3.5 w-3.5' />
+            )}
+            <span className='sr-only'>Check for latest release</span>
+          </Button>
+        </div>
+
+        <div className='mt-3 space-y-2'>
+          <div className='border-border/60 bg-card/30 grid gap-1.5 rounded-md border p-2'>
+            <div className='flex items-center justify-between gap-3'>
+              <span className='text-muted-foreground text-[10px] tracking-wide uppercase'>
+                Current
+              </span>
+              <span className='font-mono text-xs'>{versionLabel}</span>
+            </div>
+            {currentVersion?.commit ? (
+              <div className='flex items-center justify-between gap-3'>
+                <span className='text-muted-foreground text-[10px] tracking-wide uppercase'>
+                  Commit
+                </span>
+                <code className='font-mono text-[11px]'>
+                  {currentVersion.commit}
+                </code>
+              </div>
+            ) : null}
+          </div>
+
+          <div className='border-border/60 bg-card/30 grid gap-1.5 rounded-md border p-2'>
+            <div className='flex items-center justify-between gap-3'>
+              <span className='text-muted-foreground text-[10px] tracking-wide uppercase'>
+                Latest release
+              </span>
+              <span className='font-mono text-xs'>
+                {releaseQuery.isLoading
+                  ? 'loading…'
+                  : releaseQuery.isError
+                    ? 'unavailable'
+                    : releaseRateLimited
+                      ? 'rate-limited'
+                      : (releaseQuery.data?.tag_name ?? 'unknown')}
+              </span>
+            </div>
+            {releaseQuery.data?.published_at ? (
+              <div className='flex items-center justify-between gap-3'>
+                <span className='text-muted-foreground text-[10px] tracking-wide uppercase'>
+                  Published
+                </span>
+                <span className='text-[11px]'>
+                  {formatReleaseDate(releaseQuery.data.published_at)}
+                </span>
+              </div>
+            ) : null}
+          </div>
+
+          {releaseQuery.isError ? (
+            <p className='text-muted-foreground text-[11px]'>
+              Failed to fetch latest release from GitHub.
+            </p>
+          ) : releaseRateLimited ? (
+            <p className='text-muted-foreground text-[11px]'>
+              GitHub rate limit reached. Try again later.
+            </p>
+          ) : null}
+        </div>
+
+        <div className='border-border/60 mt-3 border-t pt-2'>
+          <a
+            href={releaseQuery.data?.html_url ?? RELEASES_PAGE_URL}
+            target='_blank'
+            rel='noopener noreferrer'
+            className='text-primary inline-flex items-center gap-1 text-xs hover:underline'
+          >
+            View release changelog
+            <ExternalLinkIcon className='h-3 w-3' />
+          </a>
+        </div>
+      </PopoverContent>
+    </Popover>
+  );
+}

ui/lib/utils/version.ts

@@ -0,0 +1,72 @@
+export interface ParsedVersion {
+  raw: string;
+  base: string;
+  parts: readonly number[];
+  commit: string | null;
+}
+
+export type StatusKind =
+  | 'unknown'
+  | 'outdated'
+  | 'ahead'
+  | 'commit-drift'
+  | 'current';
+
+export function parseVersion(
+  raw: string | undefined | null
+): ParsedVersion | null {
+  if (!raw) return null;
+  const trimmed = raw.trim().replace(/^v/i, '');
+  if (!trimmed) return null;
+  const [base, commitPart] = trimmed.split('+', 2);
+  const parts = (base ?? '')
+    .split('.')
+    .map((segment) => Number.parseInt(segment, 10))
+    .filter((value) => Number.isFinite(value));
+  if (parts.length === 0) return null;
+  return {
+    raw,
+    base: base ?? '',
+    parts,
+    commit: commitPart ?? null,
+  };
+}
+
+export function compareVersionParts(
+  a: readonly number[],
+  b: readonly number[]
+): number {
+  const length = Math.max(a.length, b.length);
+  for (let i = 0; i < length; i += 1) {
+    const diff = (a[i] ?? 0) - (b[i] ?? 0);
+    if (diff !== 0) return diff;
+  }
+  return 0;
+}
+
+export function deriveStatus(
+  current: ParsedVersion | null,
+  latest: ParsedVersion | null
+): StatusKind {
+  if (!current || !latest) return 'unknown';
+  const cmp = compareVersionParts(current.parts, latest.parts);
+  if (cmp < 0) return 'outdated';
+  if (cmp > 0) return 'ahead';
+  return current.commit ? 'commit-drift' : 'current';
+}
+
+export function formatReleaseDate(iso: string | undefined): string | null {
+  if (!iso) return null;
+  const date = new Date(iso);
+  if (Number.isNaN(date.getTime())) return null;
+  return date.toLocaleDateString(undefined, {
+    year: 'numeric',
+    month: 'short',
+    day: 'numeric',
+  });
+}
+
+export function formatVersionLabel(version: ParsedVersion | null): string {
+  if (!version) return 'unknown';
+  return version.raw.startsWith('v') ? version.raw : `v${version.raw}`;
+}

ui/next.config.ts

@@ -6,6 +6,9 @@ const nextConfig: NextConfig = {
   images: {
     unoptimized: true,
   },
+  turbopack: {
+    root: __dirname,
+  },
 };
 
 export default nextConfig;

ui/package.json

@@ -1,5 +1,6 @@
 {
   "name": "routstr-service",
+  "packageManager": "pnpm@10.15.0",
   "version": "0.1.0",
   "private": true,
   "scripts": {
@@ -88,5 +89,11 @@
     "prettier-plugin-tailwindcss": "^0.7.2",
     "tailwindcss": "^4.2.0",
     "typescript": "^5.9.3"
+  },
+  "pnpm": {
+    "onlyBuiltDependencies": [
+      "sharp",
+      "unrs-resolver"
+    ]
   }
 }